EngineX-Ascend/enginex-ascend-910-vllm
11
0
Fork 1
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
7f8a1b1f7add090acef165fa96461f8fad0dd3a0
enginex-ascend-910-vllm/tests/e2e/coverage.md
Sun Ruoxi 7f8a1b1f7a init v0.23.0 
Signed-off-by: Sun Ruoxi <sunruoxi@4paradigm.com>
2026-08-27 15:11:51 +08:00

423 lines
116 KiB
Markdown
Raw Blame History

The coverage of e2e is as follows:
## 1-Card Tests
| Test file | Test method | Model | 310P | Dense | MoE | Embedding | Classification | Reranker | Mamba/SSM | Multimodal Reasoning | TP | PP | EP | PCP | DCP | Context Parallel | EPLB | Dynamic EPLB | Multistream MoE | Full Graph | Full Decode Only Graph | Default FULL_AND_PIECEWISE Graph | Piecewise Graph | Eager Mode | PD disaggregation | W8A8 | W4A8 | FP16 | LoRA | Multi-LoRA | Runtime LoRA updating | Fully sharded LoRA parameterization | Spec Decode | MTP | Eagle-3 | SFA/DSA | DSA CP | Pooling runner | Score API | Classification API | Distributed executor mp | Flash Attention 3 | FIA comparison | Chunked Prefill | Prefix Caching | CPU/KV offloading | KV transfer/events | Sleep/Wake memory | Xlite Graph | CP KV Interleave | Long Sequence | FlashComm1 env | Skipped | Conditional skip | Logprobs | Batch inference | Mixed lengths |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| _310p/test_classification_310p.py | test_qwen_pooling_classify_correctness | Howeee/Qwen2.5-1.5B-apeach | ✅ | | | | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | ✅ | |
| _310p/test_dense_model_310p.py | test_qwen3_5_dense_tp1_fp16 | Qwen/Qwen3.5-4B | ✅ | | | | | | ✅ | | | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| _310p/test_dense_model_310p.py | test_qwen3_5_dense_tp1_fp16_aclgraph | Qwen/Qwen3.5-4B | ✅ | | | | | | ✅ | | | | | | | | | | | | ✅ | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | |
| _310p/test_dense_model_310p.py | test_qwen3_dense_tp1_fp16 | Qwen/Qwen3-8B | ✅ | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| _310p/test_dense_model_310p.py | test_qwen3_dense_tp1_fp16_aclgraph | Qwen/Qwen3-8B | ✅ | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | |
| _310p/test_dense_model_310p.py | test_qwen3_dense_tp1_w8a8 | vllm-ascend/Qwen3-8B-W8A8 | ✅ | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| _310p/test_embedding_310p.py | test_bge_m3_correctness | BAAI/bge-m3 | ✅ | | | ✅ | | | | | | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | ✅ | |
| _310p/test_embedding_310p.py | test_embed_models_correctness | Qwen/Qwen3-Embedding-0.6B<br>intfloat/multilingual-e5-small | ✅ | | | ✅ | | | | | | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | ✅ | |
| _310p/test_scoring_310p.py | test_cross_encoder_score_1_to_1 | BAAI/bge-reranker-v2-m3 | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | | |
| _310p/test_scoring_310p.py | test_cross_encoder_score_1_to_N | BAAI/bge-reranker-v2-m3 | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | | |
| _310p/test_scoring_310p.py | test_cross_encoder_score_N_to_N | BAAI/bge-reranker-v2-m3 | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | | |
| _310p/test_vl_model_310p.py | test_qwen3_vl_8b_tp1_fp16 | Qwen/Qwen3-VL-8B-Instruct | ✅ | | | | | | | ✅ | | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| aclgraph/test_aclgraph_accuracy.py | test_default_full_and_piecewise_res_consistency | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| aclgraph/test_aclgraph_accuracy.py | test_full_decode_only_res_consistency | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| aclgraph/test_aclgraph_accuracy.py | test_full_res_consistency | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| aclgraph/test_aclgraph_accuracy.py | test_npugraph_ex_res_consistency | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| aclgraph/test_aclgraph_accuracy.py | test_npugraph_ex_with_static_kernel | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| aclgraph/test_aclgraph_batch_invariant.py | test_aclgraph_logprobs_bitwise_batch_invariance_bs1_vs_bsN | - | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | ✅ | ✅ | |
| aclgraph/test_aclgraph_batch_invariant.py | test_aclgraph_logprobs_without_batch_invariance_should_fail | - | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | ✅ | ✅ | |
| aclgraph/test_aclgraph_batch_invariant.py | test_aclgraph_simple_generation | - | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | ✅ | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | | | |
| aclgraph/test_aclgraph_batch_invariant.py | test_aclgraph_v1_generation_is_deterministic_across_batch_sizes_with_needle | - | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | | ✅ | |
| aclgraph/test_aclgraph_mem.py | test_aclgraph_mem_use | vllm-ascend/DeepSeek-V2-Lite-W8A8 | | | ✅ | | | | | | | | | | | | | | | | | | ✅ | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| compile/test_graphex_norm_quant_fusion.py | test_rmsnorm_quant_fusion | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| compile/test_graphex_qknorm_rope_fusion.py | test_rmsnorm_quant_fusion | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| compile/test_norm_quant_fusion.py | test_rmsnorm_quant_fusion | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| lora/test_ilama_lora.py | test_ilama_lora | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| lora/test_llama32_lora.py | test_llama_lora | - | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| lora/test_lora_with_spec_decode.py | test_batch_inference_correctness | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| lora/test_qwen35_densemodel_lora.py | test_qwen35_text_lora | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| lora/test_qwen3_multi_loras.py | test_multi_loras_with_tp_sync | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | ✅ | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | |
| lora/test_qwen3_reranker_lora.py | test_reranker_models_lora | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | ✅ | |
| model_runner_v2/test_basic.py | test_egale_spec_decoding | Qwen/Qwen3-0.6B<br>vllm-ascend/DeepSeek-V2-Lite-W8A8 | | ✅ | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | ✅ | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | ✅ | | ✅ | |
| model_runner_v2/test_basic.py | test_qwen3_dense_eager_mode | Qwen/Qwen3-0.6B<br>vllm-ascend/DeepSeek-V2-Lite-W8A8 | | ✅ | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | ✅ | ✅ | |
| model_runner_v2/test_basic.py | test_qwen3_dense_graph_mode | Qwen/Qwen3-0.6B | | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | ✅ | |
| pooling/test_classification.py | test_qwen_pooling_classify_correctness | Howeee/Qwen2.5-1.5B-apeach | | | | | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | ✅ | |
| pooling/test_embedding.py | test_bge_m3_correctness | BAAI/bge-m3 | | | | ✅ | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | ✅ | |
| pooling/test_embedding.py | test_causal_embed_models_using_prefix_caching_correctness | Qwen/Qwen3-Embedding-0.6B | | | | ✅ | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | ✅ | | | | | | | ✅ | | | | | | | | | | | ✅ | |
| pooling/test_embedding.py | test_embed_models_correctness | Qwen/Qwen3-Embedding-0.6B<br>intfloat/multilingual-e5-small | | | | ✅ | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | ✅ | |
| pooling/test_scoring.py | test_cross_encoder_score_1_to_1 | BAAI/bge-reranker-v2-m3<br>dengcao/ms-marco-MiniLM-L6-v2<br>sentence-transformers/all-MiniLM-L12-v2 | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | | |
| pooling/test_scoring.py | test_cross_encoder_score_1_to_N | BAAI/bge-reranker-v2-m3<br>dengcao/ms-marco-MiniLM-L6-v2<br>sentence-transformers/all-MiniLM-L12-v2 | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | | |
| pooling/test_scoring.py | test_cross_encoder_score_N_to_N | BAAI/bge-reranker-v2-m3<br>dengcao/ms-marco-MiniLM-L6-v2<br>sentence-transformers/all-MiniLM-L12-v2 | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | | |
| pooling/test_scoring.py | test_embedding_score_1_to_1 | BAAI/bge-reranker-v2-m3<br>dengcao/ms-marco-MiniLM-L6-v2<br>sentence-transformers/all-MiniLM-L12-v2 | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | | |
| pooling/test_scoring.py | test_embedding_score_1_to_N | BAAI/bge-reranker-v2-m3<br>dengcao/ms-marco-MiniLM-L6-v2<br>sentence-transformers/all-MiniLM-L12-v2 | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | | |
| pooling/test_scoring.py | test_embedding_score_N_to_N | BAAI/bge-reranker-v2-m3<br>dengcao/ms-marco-MiniLM-L6-v2<br>sentence-transformers/all-MiniLM-L12-v2 | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | | |
| spec_decode/test_dflash.py | test_dflash_acceptance | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | ✅ | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | | ✅ | |
| spec_decode/test_draft_parallel.py | test_parallel_drafting_acceptance | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | ✅ | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | | ✅ | |
| spec_decode/test_eagle.py | test_qwen3_vl_eagle | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| spec_decode/test_eagle.py | test_qwen_eagle3_acceptance | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | ✅ | | | | | | | | ✅ | | | | | | | | | | | | | | | ✅ | |
| spec_decode/test_extract_hidden_states.py | test_extract_hidden_states_aclgraph_mode | - | | | | | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | | | | ✅ | | | | | | | | | | | ✅ | | | | | | | | | | | | ✅ | |
| spec_decode/test_extract_hidden_states.py | test_extract_hidden_states_eager_mode | - | | | | | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | | | | ✅ | | | | | | | | | | | ✅ | | | | | | | | | | | | ✅ | |
| spec_decode/test_mtp_eagle_correctness.py | test_deepseek_mtp | wemaster/deepseek_mtp_main_random_bf16 | | ✅ | | | | | | | | | ✅ | | | | | | | | | | | ✅ | | | | | | | | | ✅ | ✅ | | | | | | | ✅ | | | | | | | | | | | | | | | ✅ | |
| spec_decode/test_ngram.py | test_ngram | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | |
| spec_decode/test_ngram_npu.py | test_ngram_npu_async_acceptance | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | ✅ | | | | | | | | ✅ | | | | | | | | | | | | | | | ✅ | |
| spec_decode/test_suffix.py | test_suffix_acceptance | - | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | |
| test_attention_fa3.py | test_fa3_vs_fia_logprobs | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | |
| test_attention_fa3.py | test_fa3_vs_fia_mixed_lengths | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | ✅ | ✅ |
| test_attention_fa3.py | test_fa3_vs_fia_single_prompt | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | |
| test_attention_fa3.py | test_fa3_vs_fia_with_chunkprefill | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | |
| test_batch_invariant.py | test_logprobs_bitwise_batch_invariance_bs1_vs_bsN | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | ✅ | ✅ | |
| test_batch_invariant.py | test_logprobs_without_batch_invariance_should_fail | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | ✅ | ✅ | |
| test_batch_invariant.py | test_simple_generation | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | | | |
| test_batch_invariant.py | test_v1_generation_is_deterministic_across_batch_sizes_with_needle | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | | ✅ | |
| test_camem.py | test_end_to_end | Qwen/Qwen3-0.6B | | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | |
| test_completion_with_prompt_embeds.py | test_mixed_prompt_embeds_and_text | Qwen/Qwen3-0.6B | | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ |
| test_cpu_offloading.py | test_cpu_offloading | Qwen/Qwen3-0.6B | | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| test_guided_decoding.py | test_guided_json_completion | - | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| test_guided_decoding.py | test_guided_regex | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| test_minicpm.py | test_minicpm | OpenBMB/MiniCPM4-0.5B<br>openbmb/MiniCPM-2B-sft-bf16 | | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| test_multi_instance.py | test_two_instances_on_single_card | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| test_multistream_overlap_shared_expert.py | test_models_with_multistream_overlap_shared_expert | vllm-ascend/DeepSeek-V2-Lite-W8A8 | | | ✅ | | | | | | | | | | | | | | ✅ | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_qwen3_0_6b.py | test_dense_default_full_and_piecewise_graph | Qwen/Qwen3-0.6B | | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| test_qwen3_5_0_8b.py | test_mamba_ssm_multimodal_reasoning_mtp_full_decode_only | Qwen/Qwen3.5-0.8B | | | | | | | ✅ | | | | | | | | | | | | ✅ | | | | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_qwen3_8b_w8a8.py | test_dense_w8a8_eagle3_full_graph | RedHatAI/Qwen3-8B-speculator.eagle3<br>vllm-ascend/Qwen3-8B-W8A8 | | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | |
| test_qwen3_embedding_0_6b.py | test_embedding_full_decode_only | Qwen/Qwen3-Embedding-0.6B | | | | ✅ | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | ✅ | |
| test_sampler.py | test_qwen3_exponential_overlap | Qwen/Qwen3-0.6B | | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| test_sampler.py | test_qwen3_prompt_logprobs | Qwen/Qwen3-0.6B | | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | |
| test_sampler.py | test_qwen3_topk | Qwen/Qwen3-0.6B | | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| test_vlm.py | test_multimodal_audio | Qwen/Qwen2-Audio-7B-Instruct | | | | | | | | ✅ | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_vlm.py | test_multimodal_vl | openai-mirror/whisper-large-v3-turbo | | | | | | | | ✅ | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_vlm.py | test_multimodal_vl_language_model_only | Qwen/Qwen3-VL-8B-Instruct | | | | | | | | ✅ | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_vlm.py | test_whisper | openai-mirror/whisper-large-v3-turbo | | | | | | | | ✅ | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_xlite.py | test_models_with_xlite_decode_only | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| test_xlite.py | test_models_with_xlite_full_mode | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
## 2-Card Tests
| Test file | Test method | Model | 310P | Dense | MoE | Embedding | Classification | Reranker | Mamba/SSM | Multimodal Reasoning | TP | PP | EP | PCP | DCP | Context Parallel | EPLB | Dynamic EPLB | Multistream MoE | Full Graph | Full Decode Only Graph | Default FULL_AND_PIECEWISE Graph | Piecewise Graph | Eager Mode | PD disaggregation | W8A8 | W4A8 | FP16 | LoRA | Multi-LoRA | Runtime LoRA updating | Fully sharded LoRA parameterization | Spec Decode | MTP | Eagle-3 | SFA/DSA | DSA CP | Pooling runner | Score API | Classification API | Distributed executor mp | Flash Attention 3 | FIA comparison | Chunked Prefill | Prefix Caching | CPU/KV offloading | KV transfer/events | Sleep/Wake memory | Xlite Graph | CP KV Interleave | Long Sequence | FlashComm1 env | Skipped | Conditional skip | Logprobs | Batch inference | Mixed lengths |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| aclgraph/test_aclgraph_capture_replay.py | test_models_aclgraph_capture_replay_metrics_dp2 | vllm-ascend/DeepSeek-V2-Lite-W8A8 | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| aclgraph/test_full_graph_mode.py | test_qwen3_moe_full_decode_only_tp2 | Qwen/Qwen3-30B-A3B | | | ✅ | | | | | | ✅ | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| aclgraph/test_full_graph_mode.py | test_qwen3_moe_full_graph_tp2 | Qwen/Qwen3-30B-A3B | | | ✅ | | | | | | ✅ | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| lora/test_ilama_lora_tp2.py | test_ilama_lora_tp2 | - | | | | | | | | | ✅ | | | | | | | | | | | | | ✅ | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| lora/test_llama32_lora_tp2.py | test_llama_lora_tp2 | - | | | | | | | | | ✅ | | | | | | | | | | | | ✅ | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| spec_decode/test_spec_decode.py | test_eagle3_sp_acceptance | - | | | | | | | | | ✅ | | | | | | | | | | | | | ✅ | | | | | | | | | ✅ | | | | | | | | ✅ | | | | | | | | | | | | ✅ | | | ✅ | |
| spec_decode/test_spec_decode.py | test_p_eagle_acceptance | - | | | | | | | | | ✅ | | | | | | | | | | | | | ✅ | | | | | | | | | ✅ | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | | ✅ | |
| spec_decode/test_spec_decode.py | test_qwen3_eagle3_pcp2_tp1 | - | | | | | | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | | | | | ✅ | | | | | | | | ✅ | | | | | | | | | | | | | | | ✅ | |
| test_data_parallel.py | test_qwen3_inference_dp2 | Qwen/Qwen3-30B-A3B<br>vllm-ascend/Qwen3-30B-A3B-W8A8 | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_deepseek_multistream_moe.py | test_deepseek_multistream_moe_tp2 | vllm-ascend/DeepSeek-V3-Pruning | | | ✅ | | | | | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | |
| test_external_launcher.py | test_qwen3_external_launcher | Qwen/Qwen3-0.6B | | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_external_launcher.py | test_qwen3_external_launcher_with_matmul_allreduce | Qwen/Qwen3-0.6B | | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | ✅ | |
| test_external_launcher.py | test_qwen3_external_launcher_with_sleepmode | Qwen/Qwen3-8B | | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_external_launcher.py | test_qwen3_external_launcher_with_sleepmode_level2 | Qwen/Qwen3-8B | | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_external_launcher.py | test_qwen3_moe_external_launcher_ep_tp2 | Qwen/Qwen3-0.6B | | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_flashcomm_distributed.py | test_deepseek_v2_lite_fc1_tp2 | vllm-ascend/DeepSeek-V2-Lite-W8A8 | | | ✅ | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | |
| test_flashcomm_distributed.py | test_qwen3_dense_fc1_tp2 | - | | | | | | | | | ✅ | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| test_flashcomm_distributed.py | test_qwen3_dense_prefetch_mlp_weight_tp2 | - | | | | | | | | | ✅ | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| test_flashcomm_distributed.py | test_qwen3_moe_fc2_oshard_tp2 | Qwen/Qwen3-30B-A3B | | | ✅ | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | ✅ | | | | |
| test_gpt_oss_distributed.py | test_gpt_oss_distributed_tp2 | - | | | | | | | | | ✅ | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| test_moe_routing_replay.py | test_qwen3_moe_routing_replay | Qwen/Qwen3-30B-A3B<br>Qwen/Qwen3.5-35B-A3B | | | ✅ | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | |
| test_offline_weight_load.py | test_qwen3_offline_load_and_sleepmode_tp2 | Qwen/Qwen3-30B-A3B | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_prefix_caching.py | test_models_prefix_cache_tp2 | Qwen/Qwen3-8B<br>deepseek-ai/DeepSeek-V2-Lite-Chat | | ✅ | ✅ | | | | | | ✅ | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | |
| test_qwen3_30b_a3b.py | test_moe_tp_ep_eplb_full_decode_only | Qwen/Qwen3-30B-A3B | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_qwen3_6_27b_fia.py | test_qwen3_6_27b_multimodel_fia_eager | Qwen/Qwen3.6-27B/ | | ✅ | | | | | | ✅ | ✅ | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_qwen3_6_27b_fia.py | test_qwen3_6_27b_multimodel_fia_acl_graph | Qwen/Qwen3.6-27B/ | | ✅ | | | | | | ✅ | ✅ | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_qwen3_vl_30b_a3b_instruct.py | test_multimodal_reasoning_pp_full_decode_only | Qwen/Qwen3-VL-30B-A3B-Instruct | | | ✅ | | | | | ✅ | | ✅ | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_sequence_parallelism_moe.py | test_sequence_parallelism_moe_patterns | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| test_shared_expert_dp.py | test_deepseek_v2_lite_enable_shared_expert_dp_tp2 | deepseek-ai/DeepSeek-V2-Lite | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| test_sp_pass.py | test_qwen3_vl_sp_tp2 | Qwen/Qwen3-VL-2B-Instruct | | | | | | | | ✅ | ✅ | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
## 4-Card Tests
| Test file | Test method | Model | 310P | Dense | MoE | Embedding | Classification | Reranker | Mamba/SSM | Multimodal Reasoning | TP | PP | EP | PCP | DCP | Context Parallel | EPLB | Dynamic EPLB | Multistream MoE | Full Graph | Full Decode Only Graph | Default FULL_AND_PIECEWISE Graph | Piecewise Graph | Eager Mode | PD disaggregation | W8A8 | W4A8 | FP16 | LoRA | Multi-LoRA | Runtime LoRA updating | Fully sharded LoRA parameterization | Spec Decode | MTP | Eagle-3 | SFA/DSA | DSA CP | Pooling runner | Score API | Classification API | Distributed executor mp | Flash Attention 3 | FIA comparison | Chunked Prefill | Prefix Caching | CPU/KV offloading | KV transfer/events | Sleep/Wake memory | Xlite Graph | CP KV Interleave | Long Sequence | FlashComm1 env | Skipped | Conditional skip | Logprobs | Batch inference | Mixed lengths |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| _310p/test_dense_model_310p.py | test_qwen3_dense_tp2_fp16 | Qwen/Qwen3-8B | ✅ | ✅ | | | | | | | ✅ | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| _310p/test_dense_model_310p.py | test_qwen3_dense_tp4_w8a8 | vllm-ascend/Qwen3-32B-W8A8 | ✅ | ✅ | | | | | | | ✅ | | | | | | | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| _310p/test_moe_model_310p.py | test_qwen3_5_moe_tp4_fp16 | Qwen/Qwen3.5-35B-A3B | ✅ | | ✅ | | | | ✅ | | ✅ | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | |
| _310p/test_moe_model_310p.py | test_qwen3_moe_tp2_w8a8 | vllm-ascend/Qwen3-30B-A3B-W8A8 | ✅ | | ✅ | | | | | | ✅ | | | | | | | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | |
| _310p/test_moe_model_310p.py | test_qwen3_moe_tp4_fp16 | Qwen/Qwen3-30B-A3B | ✅ | | ✅ | | | | | | ✅ | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | |
| _310p/test_vl_model_310p.py | test_qwen3_vl_8b_tp2_fp16 | Qwen/Qwen3-VL-8B-Instruct | ✅ | | | | | | | ✅ | | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| context_parallel/test_accuracy.py | test_accuracy_dcp_only_eager | Qwen/Qwen3-8B<br>vllm-ascend/DeepSeek-V2-Lite-W8A8 | | ✅ | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | |
| context_parallel/test_accuracy.py | test_accuracy_dcp_only_graph | Qwen/Qwen3-8B<br>vllm-ascend/DeepSeek-V2-Lite-W8A8 | | ✅ | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | |
| context_parallel/test_accuracy.py | test_accuracy_pcp_only | Qwen/Qwen3-8B<br>vllm-ascend/DeepSeek-V2-Lite-W8A8 | | ✅ | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | |
| context_parallel/test_accuracy.py | test_models_long_sequence_cp_kv_interleave_size_output_between_tp_and_cp | vllm-ascend/DeepSeek-V2-Lite-W8A8 | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| context_parallel/test_accuracy.py | test_models_long_sequence_output_between_tp_and_cp | vllm-ascend/DeepSeek-V2-Lite-W8A8 | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | |
| context_parallel/test_basic.py | test_dcp_basic | deepseek-ai/DeepSeek-V2-Lite-Chat | | | ✅ | | | | | | ✅ | | ✅ | | ✅ | ✅ | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | |
| context_parallel/test_basic.py | test_dcp_full_graph | deepseek-ai/DeepSeek-V2-Lite-Chat | | | ✅ | | | | | | ✅ | | ✅ | | ✅ | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | |
| context_parallel/test_basic.py | test_dcp_piece_wise | deepseek-ai/DeepSeek-V2-Lite-Chat | | | ✅ | | | | | | ✅ | | ✅ | | ✅ | ✅ | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | |
| context_parallel/test_basic.py | test_deepseek_v4_w4a8_dsa_cp_basic_greedy | gdydems/DeepSeek-V4-Flash-w4a8-mtp | | | ✅ | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | | ✅ | | | | | | | | | ✅ | | | | | | | | | | | | | | | ✅ | ✅ | | ✅ | | ✅ | |
| context_parallel/test_basic.py | test_models_pcp_dcp_basic | Qwen/Qwen3-Next-80B-A3B-Instruct<br>deepseek-ai/DeepSeek-V2-Lite-Chat<br>vllm-ascend/DeepSeek-V3.2-W8A8-Pruning<br>vllm-ascend/Qwen3-30B-A3B-W8A8 | | | ✅ | | | | | | ✅ | | ✅ | ✅ | ✅ | ✅ | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | |
| context_parallel/test_basic.py | test_models_pcp_dcp_full_graph | deepseek-ai/DeepSeek-V2-Lite-Chat<br>vllm-ascend/Qwen3-30B-A3B-W8A8 | | | ✅ | | | | | | ✅ | | ✅ | ✅ | ✅ | ✅ | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | |
| context_parallel/test_basic.py | test_models_pcp_dcp_piece_wise | deepseek-ai/DeepSeek-V2-Lite-Chat<br>vllm-ascend/Qwen3-30B-A3B-W8A8 | | | ✅ | | | | | | ✅ | | ✅ | ✅ | ✅ | ✅ | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | |
| context_parallel/test_basic.py | test_pcp_basic | deepseek-ai/DeepSeek-V2-Lite-Chat | | | ✅ | | | | | | ✅ | | ✅ | ✅ | | ✅ | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | |
| context_parallel/test_basic.py | test_pcp_full_graph | deepseek-ai/DeepSeek-V2-Lite-Chat | | | ✅ | | | | | | ✅ | | ✅ | ✅ | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | |
| context_parallel/test_basic.py | test_pcp_piece_wise | deepseek-ai/DeepSeek-V2-Lite-Chat | | | ✅ | | | | | | ✅ | | ✅ | ✅ | | ✅ | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | |
| context_parallel/test_basic.py | test_qwen3_5_4b_multimodal_single_and_multi_image | Qwen/Qwen3.5-4B | | | | | | | ✅ | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | ✅ | | | |
| context_parallel/test_basic.py | test_qwen3_vl_8b_multimodal_single_and_multi_image | Qwen/Qwen3-VL-8B-Instruct | | | | | | | | ✅ | ✅ | | | ✅ | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | ✅ | | | |
| context_parallel/test_chunked_prefill_cp.py | test_models_chunked_prefill_mixed_length_prompts_including_1_token | vllm-ascend/DeepSeek-V2-Lite-W8A8<br>vllm-ascend/Qwen3-30B-A3B-W8A8 | | | ✅ | | | | | | ✅ | | ✅ | ✅ | | ✅ | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | ✅ |
| context_parallel/test_chunked_prefill_cp.py | test_models_chunked_prefill_with_cp_basic | vllm-ascend/DeepSeek-V2-Lite-W8A8<br>vllm-ascend/Qwen3-30B-A3B-W8A8 | | | ✅ | | | | | | | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | | ✅ | | | | | | |
| context_parallel/test_chunked_prefill_cp.py | test_models_chunked_prefill_with_cp_default_full_and_piecewise | vllm-ascend/DeepSeek-V2-Lite-W8A8<br>vllm-ascend/Qwen3-30B-A3B-W8A8 | | | ✅ | | | | | | | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | | ✅ | | | | | | |
| context_parallel/test_chunked_prefill_cp.py | test_models_chunked_prefill_with_cp_full_graph | vllm-ascend/DeepSeek-V2-Lite-W8A8<br>vllm-ascend/Qwen3-30B-A3B-W8A8 | | | ✅ | | | | | | | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | | ✅ | | | | | | |
| context_parallel/test_chunked_prefill_cp.py | test_models_chunked_prefill_with_empty_kvcache | vllm-ascend/DeepSeek-V2-Lite-W8A8<br>vllm-ascend/Qwen3-30B-A3B-W8A8 | | | ✅ | | | | | | ✅ | | ✅ | ✅ | | ✅ | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | ✅ | ✅ | | ✅ | | | ✅ | |
| context_parallel/test_mtp.py | test_dcp_mtp3_full_graph | - | | | | | | | | | ✅ | | ✅ | | ✅ | ✅ | | | | | ✅ | | | | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| context_parallel/test_mtp.py | test_pcp_dcp_mtp1_eager | - | | | | | | | | | ✅ | | ✅ | ✅ | ✅ | ✅ | | | | | | | | ✅ | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| context_parallel/test_mtp.py | test_pcp_dcp_mtp3_eager | - | | | | | | | | | ✅ | | ✅ | ✅ | ✅ | ✅ | | | | | | | | ✅ | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| context_parallel/test_mtp.py | test_pcp_dcp_mtp3_full_graph | - | | | | | | | | | ✅ | | ✅ | ✅ | ✅ | ✅ | | | | | ✅ | | | | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| context_parallel/test_mtp.py | test_pcp_dcp_mtp3_piecewise_graph | - | | | | | | | | | ✅ | | ✅ | ✅ | ✅ | ✅ | | | | | | | ✅ | | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| context_parallel/test_mtp.py | test_pcp_eagle3_eager | - | | | | | | | | | ✅ | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | ✅ | | | | | | |
| context_parallel/test_prefix_caching_cp.py | test_models_prefix_cache_with_cp_basic | vllm-ascend/DeepSeek-V2-Lite-W8A8<br>vllm-ascend/Qwen3-30B-A3B-W8A8 | | | ✅ | | | | | | | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | ✅ | | | | | | |
| context_parallel/test_prefix_caching_cp.py | test_models_prefix_cache_with_cp_default_full_and_piecewise | vllm-ascend/DeepSeek-V2-Lite-W8A8<br>vllm-ascend/Qwen3-30B-A3B-W8A8 | | | ✅ | | | | | | | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | ✅ | | | | | | |
| context_parallel/test_prefix_caching_cp.py | test_models_prefix_cache_with_cp_full_graph | vllm-ascend/DeepSeek-V2-Lite-W8A8<br>vllm-ascend/Qwen3-30B-A3B-W8A8 | | | ✅ | | | | | | | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | ✅ | | | | | | |
| spec_decode/test_mtp_qwen3_next.py | test_qwen3_next_mtp_acceptance_tp4 | Qwen/Qwen3-Next-80B-A3B-Instruct | | | ✅ | | | | | | ✅ | | | | | | | | | | | | | ✅ | | | | | | | | | ✅ | ✅ | | | | | | | ✅ | | | | | | | | | | | | | | | ✅ | |
| test_data_parallel_tp2.py | test_qwen3_inference_dp2_tp2 | Qwen/Qwen3-30B-A3B | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_deepseek_v3_2_w8a8_pruning.py | test_moe_w8a8_tp_pp_ep_full_decode_only | vllm-ascend/DeepSeek-V3.2-W8A8-Pruning | | | ✅ | | | | | | ✅ | ✅ | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| test_deepseek_v3_2_w8a8_pruning.py | test_pd_disaggregation_w8a8_sfa_dsa_full_decode_only | vllm-ascend/DeepSeek-V3.2-W8A8-Pruning | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | ✅ | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_deepseek_v4.py | test_deepseek_v4_w4a8_tp4_basic_greedy | gdydems/DeepSeek-V4-Flash-w4a8-mtp | | | ✅ | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_deepseek_v4.py | test_deepseek_v4_w4a8_tp4_index_cache_freq4 | gdydems/DeepSeek-V4-Flash-w4a8-mtp | | | ✅ | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_pipeline_parallel.py | test_models_pp2_dp2 | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| test_pipeline_parallel.py | test_models_pp2_tp2 | - | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| test_profiling_chunk_performance.py | test_profiling_chunk_ttft_performance | - | | | | | | | | | ✅ | ✅ | ✅ | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | ✅ | | | | | | |
| test_qwen3_5.py | test_qwen3_5_27b_distributed_mp_tp4 | Qwen/Qwen3.5-27B | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | |
| test_qwen3_5.py | test_qwen3_5_35b_distributed_mp_tp4 | Qwen/Qwen3.5-35B-A3B | | | ✅ | | | | ✅ | | ✅ | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | |
| test_qwen3_5.py | test_qwen3_5_35b_distributed_mp_tp4_full_decode_only_mtp3 | Qwen/Qwen3.5-35B-A3B | | | ✅ | | | | ✅ | | ✅ | | | | | | | | | | ✅ | | | | | | | | | | | | ✅ | ✅ | | | | | | | ✅ | | | | | | | | | | | | | | | ✅ | |
| test_qwen3_5.py | test_qwen3_5_35b_distributed_mp_tp4_full_decode_only_mtp3_flashcomm | Qwen/Qwen3.5-35B-A3B | | | ✅ | | | | ✅ | | | | | | | | | | | | | | | ✅ | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| test_qwen3_next.py | test_qwen3_next_distributed_mp_flash_comm_tp4 | Qwen/Qwen3-Next-80B-A3B-Instruct | | | ✅ | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | |
| test_qwen3_next.py | test_qwen3_next_distributed_mp_full_decode_only_tp4 | Qwen/Qwen3-Next-80B-A3B-Instruct | | | ✅ | | | | | | ✅ | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | |
| test_qwen3_next.py | test_qwen3_next_distributed_mp_graph_mode_tp4 | Qwen/Qwen3-Next-80B-A3B-Instruct | | | ✅ | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | |
| test_qwen3_next.py | test_qwen3_next_distributed_mp_tp4 | Qwen/Qwen3-Next-80B-A3B-Instruct | | | ✅ | | | | | | ✅ | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | |
| test_qwen3_next.py | test_qwen3_next_w8a8dynamic_distributed_tp4_ep | vllm-ascend/Qwen3-Next-80B-A3B-Instruct-W8A8 | | | ✅ | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
## Nightly Tests
| Test file | Test method | Model | 310P | Dense | MoE | Embedding | Classification | Reranker | Mamba/SSM | Multimodal Reasoning | TP | PP | EP | PCP | DCP | Context Parallel | EPLB | Dynamic EPLB | Multistream MoE | Full Graph | Full Decode Only Graph | Default FULL_AND_PIECEWISE Graph | Piecewise Graph | Eager Mode | PD disaggregation | W8A8 | W4A8 | FP16 | LoRA | Multi-LoRA | Runtime LoRA updating | Fully sharded LoRA parameterization | Spec Decode | MTP | Eagle-3 | SFA/DSA | DSA CP | Pooling runner | Score API | Classification API | Distributed executor mp | Flash Attention 3 | FIA comparison | Chunked Prefill | Prefix Caching | CPU/KV offloading | KV transfer/events | Sleep/Wake memory | Xlite Graph | CP KV Interleave | Long Sequence | FlashComm1 env | Skipped | Conditional skip | Logprobs | Batch inference | Mixed lengths |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 310p/single_node/ops/singlecard_ops/test_recurrent_gated_delta_rule_v310.py | test_recurrent_gated_delta_rule_v310 | - | ✅ | | | | | | | | | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| multi_node/external_dp/config/GLM5_1-W8A8-EP-external.yaml | multi-node-glm-5.1-w8a8-ep-external-dp | Eco-Tech/GLM-5.1-w8a8 | | ✅ | | | | | | | | | ✅ | | | | | | | | | | | ✅ | ✅ | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | | | | ✅ | | | | ✅ | ✅ | | | | | |
| multi_node/external_dp/scripts/test_external_dp.py | test_external_dp | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| multi_node/internal_dp/config/DeepSeek-R1-W8A8-EPLB.yaml | test DeepSeek-R1-W8A8 disaggregated_prefill | vllm-ascend/DeepSeek-R1-0528-W8A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | ✅ | | | | | | | ✅ | ✅ | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | |
| multi_node/internal_dp/config/DeepSeek-R1-W8A8-longseq.yaml | test DeepSeek-R1-W8A8-longseq disaggregated_prefill | vllm-ascend/DeepSeek-R1-0528-W8A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | ✅ | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | ✅ | | | ✅ | | | ✅ | ✅ | | | | | | |
| multi_node/internal_dp/config/DeepSeek-R1-W8A8.yaml | test DeepSeek-R1-W8A8 disaggregated_prefill | vllm-ascend/DeepSeek-R1-0528-W8A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | ✅ | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | |
| multi_node/internal_dp/config/DeepSeek-V3.1-BF16.yaml | test DeepSeek-V3.1-BF16 on A3 | unsloth/DeepSeek-V3.1-BF16 | | | ✅ | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | | | | | | | |
| multi_node/internal_dp/config/DeepSeek-V3_2-W8A8-A3-dual-nodes.yaml | test DeepSeek-V3.2-W8A8 on A3 | vllm-ascend/DeepSeek-V3.2-W8A8 | | | ✅ | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| multi_node/internal_dp/config/DeepSeek-V3_2-W8A8-EP.yaml | test DeepSeek-V3.2-W8A8-EP disaggregated_prefill | vllm-ascend/DeepSeek-V3.2-W8A8 | | | ✅ | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | ✅ | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | |
| multi_node/internal_dp/config/GLM5_1-W8A8-A2-dual-nodes.yaml | multi-node-GLM-5.1-w8a8-A2 | Eco-Tech/GLM-5.1-w8a8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | ✅ | | ✅ | | | | | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| multi_node/internal_dp/config/GLM5_1-W8A8-A3-dual-nodes.yaml | multi-node-GLM-5.1-w8a8-A3 | Eco-Tech/GLM-5.1-w8a8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | ✅ | | ✅ | | | | | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | ✅ | | | | | | | ✅ | | | | | | |
| multi_node/internal_dp/config/GLM5_1-W8A8-EP.yaml | multi-node-GLM-5.1-w8a8-EP | Eco-Tech/GLM-5.1-w8a8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | ✅ | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | |
| multi_node/internal_dp/config/Kimi-K2_5-W4A8-A2-dual-nodes.yaml | test Kimi-K2.5-W4A8 A2 dual nodes | Eco-Tech/Kimi-K2.5-W4A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | | ✅ | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | ✅ | | | | | | |
| multi_node/internal_dp/config/Qwen3-235B-A22B-A2.yaml | test Qwen3-235B-A22B multi-dp on A2 | Qwen/Qwen3-235B-A22B | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| multi_node/internal_dp/config/Qwen3-235B-A22B.yaml | test Qwen3-235B-A22B multi-dp | Qwen/Qwen3-235B-A22B | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| multi_node/internal_dp/config/Qwen3-235B-W8A8-EPLB.yaml | test Qwen3-235B-A22B-W8A8 disaggregated_prefill | vllm-ascend/Qwen3-235B-A22B-W8A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | ✅ | | | | | | | ✅ | ✅ | ✅ | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | |
| multi_node/internal_dp/config/Qwen3-235B-W8A8-longseq.yaml | test Qwen3-235B-A22B-W8A8-longseq disaggregated_prefill | vllm-ascend/Qwen3-235B-A22B-W8A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | ✅ | ✅ | | | | | | | | | | | | | | | | | | | | | ✅ | | | ✅ | | | | | | | |
| multi_node/internal_dp/config/Qwen3-235B-W8A8.yaml | test Qwen3-235B-A22B-W8A8 disaggregated_prefill | vllm-ascend/Qwen3-235B-A22B-W8A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | ✅ | ✅ | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | |
| multi_node/internal_dp/config/Qwen3-235B-disagg-pd.yaml | test Qwen3-235B-A22B disaggregated_prefill | Qwen/Qwen3-235B-A22B | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | |
| multi_node/internal_dp/config/Qwen3-VL-235B-disagg-pd.yaml | test Qwen3-VL-235B-A22B disaggregated_prefill | Qwen/Qwen3-VL-235B-A22B-Instruct | | | | | | | | ✅ | ✅ | | ✅ | | | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | |
| single_node/models/configs/DeepSeek-R1-0528-W8A8.yaml | DeepSeek-R1-0528-W8A8-EPLB | vllm-ascend/DeepSeek-R1-0528-W8A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/models/configs/DeepSeek-R1-0528-W8A8.yaml | DeepSeek-R1-0528-W8A8-aclgraph | vllm-ascend/DeepSeek-R1-0528-W8A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/models/configs/DeepSeek-R1-0528-W8A8.yaml | DeepSeek-R1-0528-W8A8-single | vllm-ascend/DeepSeek-R1-0528-W8A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/models/configs/DeepSeek-V3.2-W8A8.yaml | DeepSeek-V3.2-W8A8-TP8-DP2 | vllm-ascend/DeepSeek-V3.2-W8A8 | | | ✅ | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | |
| single_node/models/configs/DeepSeek-V4-Flash-W8A8-A3.yaml | DeepSeek-V4-Flash-W8A8-A3 | Eco-Tech/DeepSeek-V4-Flash-w8a8-mtp | | | ✅ | | | | | | ✅ | | ✅ | | | | | | ✅ | | ✅ | | | | | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | | ✅ | | | | | | ✅ | ✅ | | | | | |
| single_node/models/configs/GLM-4.7.yaml | GLM-4.7-TP8-DP2-decodegraph | Eco-Tech/GLM-4.7-W8A8-floatmtp | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/models/configs/Hy3-preview.yaml | Hy3-preview-TP16-EP-MTP | Tencent-Hunyuan/Hy3-preview | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/models/configs/Kimi-K2-Thinking.yaml | Kimi-K2-Thinking-TP16-Case | moonshotai/Kimi-K2-Thinking | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/models/configs/Kimi-K2.5.yaml | Kimi-K2.5-W4A8-Case | Eco-Tech/Kimi-K2.5-W4A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | | ✅ | | | | | | ✅ | | ✅ | | | | | | | | | ✅ | ✅ | | | | | | ✅ | ✅ | | | | | |
| single_node/models/configs/MTPX-DeepSeek-R1-0528-W8A8.yaml | MTPX-DeepSeek-R1-0528-W8A8-mtp2 | vllm-ascend/DeepSeek-R1-0528-W8A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/models/configs/MTPX-DeepSeek-R1-0528-W8A8.yaml | MTPX-DeepSeek-R1-0528-W8A8-mtp3 | vllm-ascend/DeepSeek-R1-0528-W8A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/models/configs/MiniMax-M2.5-w8a8-QuaRot-A2.yaml | MiniMax-M2.5-w8a8 | Eco-Tech/MiniMax-M2.5-w8a8-QuaRot | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | | ✅ | ✅ | | | | | |
| single_node/models/configs/MiniMax-M2.5-w8a8-QuaRot-A3.yaml | MiniMax-M2.5-w8a8 | Eco-Tech/MiniMax-M2.5-w8a8-QuaRot | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | |
| single_node/models/configs/Prefix-Cache-DeepSeek-R1-0528-W8A8.yaml | prefix-cache-deepseek-r1-0528-w8a8 | vllm-ascend/DeepSeek-R1-0528-W8A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/models/configs/Prefix-Cache-Qwen3-32B-Int8.yaml | prefix-cache-qwen3-32b-w8a8 | vllm-ascend/Qwen3-32B-W8A8 | | ✅ | | | | | | | ✅ | | | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/models/configs/Qwen3-235B-A22B-W8A8.yaml | Qwen3-235B-A22B-W8A8-EPLB | vllm-ascend/Qwen3-235B-A22B-W8A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | |
| single_node/models/configs/Qwen3-235B-A22B-W8A8.yaml | Qwen3-235B-A22B-W8A8-full_graph | vllm-ascend/Qwen3-235B-A22B-W8A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | |
| single_node/models/configs/Qwen3-235B-A22B-W8A8.yaml | Qwen3-235B-A22B-W8A8-piecewise | vllm-ascend/Qwen3-235B-A22B-W8A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | |
| single_node/models/configs/Qwen3-30B-A3B-W4A8-llm-compressor.yaml | Qwen3-30B-A3B-W4A8-llm-compressor | vllm-ascend/Qwen3-30B-A3B-Instruct-2507-quantized.w4a8 | | | ✅ | | | | | | ✅ | | | | | | | | | | ✅ | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/models/configs/Qwen3-30B-A3B-W8A8.yaml | Qwen3-30B-A3B-W8A8-TP1 | vllm-ascend/Qwen3-30B-A3B-W8A8 | | | ✅ | | | | | | | | | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/models/configs/Qwen3-30B-QuaRot-eagle3.yaml | Qwen3-30B-QuaRot | vllm-ascend/Qwen3-30B-A3B-W8A8-QuaRot | | | ✅ | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | ✅ | | ✅ | | | | | | ✅ | | | | | | | | | | | | | | | | |
| single_node/models/configs/Qwen3-32B-Int8-A2.yaml | Qwen3-32B-W8A8-aclgraph-a2 | vllm-ascend/Qwen3-32B-W8A8 | | ✅ | | | | | | | ✅ | | | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/models/configs/Qwen3-32B-Int8-A2.yaml | Qwen3-32B-W8A8-single-a2 | vllm-ascend/Qwen3-32B-W8A8 | | ✅ | | | | | | | ✅ | | | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/models/configs/Qwen3-32B-Int8.yaml | Qwen3-32B-W8A8-aclgraph-a3 | vllm-ascend/Qwen3-32B-W8A8 | | ✅ | | | | | | | ✅ | | | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/models/configs/Qwen3-32B-Int8.yaml | Qwen3-32B-W8A8-single-a3 | vllm-ascend/Qwen3-32B-W8A8 | | ✅ | | | | | | | ✅ | | | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/models/configs/Qwen3-32B-QuaRot-eagle3.yaml | Qwen3-32B-QuaRot | vllm-ascend/Qwen3-32B-W8A8-QuaRot | | ✅ | | | | | | | ✅ | | | | | | | | | | | | | ✅ | | ✅ | | | | | | | ✅ | | ✅ | | | | | | ✅ | | | | | | | | | | | | | | | | |
| single_node/models/configs/Qwen3-VL-235B-A22B-Instruct-W8A8.yaml | Qwen3-VL-235B-A22B-Instruct-W8A8 | Eco-Tech/Qwen3-VL-235B-A22B-Instruct-w8a8-QuaRot | | | | | | | | ✅ | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | |
| single_node/models/configs/Qwen3-VL-32B-Instruct-W8A8.yaml | Qwen3-VL-32B-Instruct-W8A8 | Eco-Tech/Qwen3-VL-32B-Instruct-w8a8-QuaRot | | | | | | | | ✅ | ✅ | | | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | |
| single_node/models/configs/Qwen3.5-122B-A10B-W8A8-A3.yaml | Qwen3.5-122B-A10B-W8A8-A3 | Eco-Tech/Qwen3.5-122B-A10B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | |
| single_node/models/configs/Qwen3.5-27B-w8a8-A2.yaml | Qwen3.5-27B-w8a8 | Eco-Tech/Qwen3.5-27B-w8a8-mtp | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/models/configs/Qwen3.5-27B-w8a8-A3.yaml | Qwen3.5-27B-w8a8 | Eco-Tech/Qwen3.5-27B-w8a8-mtp | | | | | | | ✅ | | ✅ | | | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/models/configs/Qwen3.5-397B-A17B-W8A8-mtp-A3.yaml | Qwen3.5-397B-A17B-w8a8-mtp | Eco-Tech/Qwen3.5-397B-A17B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/models/configs/Qwen3.5-397B-A17B-w4a8-mtp-A2.yaml | Qwen3.5-397B-A17B-w4a8-mtp | Eco-Tech/Qwen3.5-397B-A17B-w4a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | ✅ | | ✅ | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/ops/multicard_ops_a2/test_matmul_allreduce_add_rmsnorm.py | test_matmul_allreduce_add_rmsnorm_kernel | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/multicard_ops_a3/test_dispatch_ffn_combine.py | test_dispatch_ffn_combine_kernel | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/multicard_ops_a3/test_dispatch_ffn_combine_bf16.py | test_dispatch_ffn_combine_kernel | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/multicard_ops_a3/test_dispatch_ffn_combine_w4a8.py | test_dispatch_ffn_combine_kernel | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/multicard_ops_a3/test_dispatch_gmm_combine_decode.py | test_dispatch_gmm_combine_decode_base | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/multicard_ops_a3/test_dispatch_gmm_combine_decode.py | test_dispatch_gmm_combine_decode_dynamic_eplb | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/multicard_ops_a3/test_dispatch_gmm_combine_decode.py | test_dispatch_gmm_combine_decode_with_mc2_mask | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_add_rms_norm_bias.py | test_quant_fpx_linear | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_batch_matmul_transpose.py | test_boundary_conditions | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_batch_matmul_transpose.py | test_random_shapes | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_batch_matmul_transpose.py | test_zero_values | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_bgmv_expand.py | test_bgmv_expand | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_bgmv_shrink.py | test_bgmv_shrink | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_causal_conv1d_310.py | test_ascend_causal_conv1d_310_fn | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | |
| single_node/ops/singlecard_ops/test_causal_conv1d_310.py | test_causal_conv1d_310_update | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | |
| single_node/ops/singlecard_ops/test_copy_and_expand_eagle_inputs.py | test_copy_and_expand_eagle_inputs | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_copy_and_expand_eagle_inputs.py | test_large_tokens_per_request | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_copy_and_expand_eagle_inputs.py | test_large_tokens_shift_true | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_copy_and_expand_eagle_inputs.py | test_minimal_case | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_copy_and_expand_eagle_inputs.py | test_no_rejected_tokens | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_dequant_swiglu_quant.py | test_npu_dequant_swiglu_quant_with_limit | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_fused_gdn_gating.py | test_fused_gdn_gating_bulk_dma_alignment | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_fused_gdn_gating.py | test_fused_gdn_gating_extreme_large_batch | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| single_node/ops/singlecard_ops/test_fused_gdn_gating.py | test_fused_gdn_gating_large_batch_multi_row | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| single_node/ops/singlecard_ops/test_fused_gdn_gating.py | test_fused_gdn_gating_non_bulk_dma_fallback | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_fused_gdn_gating.py | test_fused_gdn_gating_non_default_params | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_fused_gdn_gating.py | test_fused_gdn_gating_output_shapes | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_fused_gdn_gating.py | test_fused_gdn_gating_small_batch_optimization | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| single_node/ops/singlecard_ops/test_fused_gdn_gating.py | test_fused_gdn_gating_vs_reference | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_fused_moe.py | test_select_experts | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| single_node/ops/singlecard_ops/test_fused_moe.py | test_select_experts_invalid_scoring_func | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| single_node/ops/singlecard_ops/test_fused_moe.py | test_token_dispatcher_with_all_gather | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| single_node/ops/singlecard_ops/test_fused_moe.py | test_token_dispatcher_with_all_gather_quant | - | | | | | | | | | | | | | | | | ✅ | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| single_node/ops/singlecard_ops/test_gating_top_k_softmax.py | test_quant_fpx_linear | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_gmm_swiglu_quant_weight_nz_tensor_list.py | test_gmm_swiglu_quant_weight_nz_tensor_list | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_grouped_matmul_swiglu_quant.py | test_grouped_matmul_swiglu_quant_kernel | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_hamming_dist_top_k.py | test_hamming_dist_top_k | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_hamming_dist_top_k.py | test_hamming_dist_top_k_compare | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_mla_preprocess.py | test_mla_preprocess_kernel | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| single_node/ops/singlecard_ops/test_mla_preprocess_nq.py | test_mla_preprocess_kernel | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| single_node/ops/singlecard_ops/test_mla_preprocess_qdown.py | test_mla_preprocess_kernel | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| single_node/ops/singlecard_ops/test_moe_init_routing_custom.py | test_moe_init_routing_custom | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_ngram_spec_decode.py | test_ngram_spec_decode_attrs | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_ngram_spec_decode.py | test_ngram_spec_decode_basic | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_ngram_spec_decode.py | test_ngram_spec_decode_decode | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_ngram_spec_decode.py | test_ngram_spec_decode_discard | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_ngram_spec_decode.py | test_ngram_spec_decode_exact_match | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_ngram_spec_decode.py | test_ngram_spec_decode_full_capacity | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_ngram_spec_decode.py | test_ngram_spec_decode_k1 | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_ngram_spec_decode.py | test_ngram_spec_decode_minimal | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_ngram_spec_decode.py | test_ngram_spec_decode_no_valid_sampled | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_ngram_spec_decode.py | test_ngram_spec_decode_padding | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_ngram_spec_decode.py | test_ngram_spec_decode_prefill | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_npu_hc_pre.py | test_npu_hc_pre_v1_v2_bf16_3d_input | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_npu_hc_pre.py | test_npu_hc_pre_v1_v2_bf16_4d_input | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_npu_moe_gating_top_k.py | test_npu_moe_gating_topk_compare | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_recurrent_gated_delta_rule.py | test_recurrent_gated_delta_rule | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_recurrent_gated_delta_rule.py | test_recurrent_gated_delta_rule_no_accepted | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_recurrent_gated_delta_rule_310.py | test_fused_recurrent_gated_delta_rule_310 | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | |
| single_node/ops/singlecard_ops/test_reshape_and_cache_bnsd.py | test_reshape_and_cache_bnsd_bf16_shape | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_reshape_and_cache_bnsd.py | test_reshape_and_cache_bnsd_compare | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_reshape_and_cache_bnsd.py | test_reshape_and_cache_bnsd_with_expected_output | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_transpose_kv_cache_by_block.py | test_transpose_kv_cache_by_block | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/test_vocabparallelembedding.py | test_get_masked_input_and_mask | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_apply_penalties_triton.py | test_apply_all_penalties_v1_vs_ascend | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| single_node/ops/singlecard_ops/triton/test_bad_words.py | test_apply_bad_words_different_shapes | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_bad_words.py | test_apply_bad_words_edge_cases | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_bad_words.py | test_apply_bad_words_no_bad_words | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_bad_words.py | test_apply_bad_words_token_limit | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_batch_memcpy.py | test_batch_memcpy | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| single_node/ops/singlecard_ops/triton/test_bincount.py | test_bincount_kernel | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| single_node/ops/singlecard_ops/triton/test_causal_conv1d.py | test_ascend_causal_conv1d | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_causal_conv1d.py | test_causal_conv1d | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| single_node/ops/singlecard_ops/triton/test_causal_conv1d.py | test_causal_conv1d_update_qwen3_next_shape | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| single_node/ops/singlecard_ops/triton/test_causal_conv1d.py | test_causal_conv1d_update_with_batch_gather | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | ✅ | |
| single_node/ops/singlecard_ops/triton/test_chunk_gated_delta_rule.py | test_chunk_gated_delta_rule_310_state_layout_matches_vllm | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_chunk_gated_delta_rule.py | test_triton_fusion_ops | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_clear_ssm_states.py | test_clear_ssm_states_ref_parity | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_compute_slot_mapping.py | test_compute_slot_mapping_npu_kernel | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_compute_token_logprobs.py | test_topk_log_softmax_deterministic | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| single_node/ops/singlecard_ops/triton/test_compute_token_logprobs.py | test_topk_log_softmax_dtypes | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| single_node/ops/singlecard_ops/triton/test_compute_token_logprobs.py | test_topk_log_softmax_edge_cases | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| single_node/ops/singlecard_ops/triton/test_compute_token_logprobs.py | test_topk_log_softmax_kernel | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| single_node/ops/singlecard_ops/triton/test_compute_topk_logprobs.py | test_compute_topk_logprobs | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_fused_gdn_gating.py | test_fused_gdn_gating_310p_parity_precision | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_fused_qkvzba_split_reshape_cat.py | test_fused_qkvzba_split_reshape_cat | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_fused_recurrent_gated_delta_rule.py | test_fused_recurrent_gated_delta_rule_310_state_layout_matches_vllm | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_fused_recurrent_gated_delta_rule.py | test_fused_recurrent_gated_delta_rule_310p_parity_precision | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| single_node/ops/singlecard_ops/triton/test_fused_sigmoid_gating_delta_rule.py | test_triton_fusion_ops | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_l2norm.py | test_l2norm | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_log_softmax.py | test_topk_log_softmax_kernel | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_min_p.py | test_apply_min_p_kernel | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_mrope.py | test_mrotary_embedding_triton_kernel | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_muls_add.py | test_muls_add_triton_correctness | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_penality.py | test_apply_penalties | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| single_node/ops/singlecard_ops/triton/test_post_update.py | test_post_update | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | |
| single_node/ops/singlecard_ops/triton/test_prepare_inputs_padded.py | test_prepare_inputs_padded | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_rejection_sample.py | test_rejection_random_sample | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| single_node/ops/singlecard_ops/triton/test_rejection_sample.py | test_rejection_sampler_block_verify_triton_kernel | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | |
| single_node/ops/singlecard_ops/triton/test_rope.py | test_rotary_embedding_triton_kernel | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_rope.py | test_rotary_embedding_triton_kernel_siso | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_rope.py | test_rotary_embedding_triton_kernel_with_cos_sin_cache | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_split_qkv_rmsnorm_mrope.py | test_split_qkv_rmsnorm_mrope | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_split_qkv_rmsnorm_rope.py | test_split_qkv_rmsnorm_rope | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_split_qkv_rmsnorm_rope.py | test_split_qkv_rmsnorm_rope_with_bias | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_split_qkv_tp_rmsnorm_rope.py | test_split_qkv_tp_rmsnorm_rope | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/ops/singlecard_ops/triton/test_temperature.py | test_temperature_kernel | - | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
## Weekly Tests
| Test file | Test method | Model | 310P | Dense | MoE | Embedding | Classification | Reranker | Mamba/SSM | Multimodal Reasoning | TP | PP | EP | PCP | DCP | Context Parallel | EPLB | Dynamic EPLB | Multistream MoE | Full Graph | Full Decode Only Graph | Default FULL_AND_PIECEWISE Graph | Piecewise Graph | Eager Mode | PD disaggregation | W8A8 | W4A8 | FP16 | LoRA | Multi-LoRA | Runtime LoRA updating | Fully sharded LoRA parameterization | Spec Decode | MTP | Eagle-3 | SFA/DSA | DSA CP | Pooling runner | Score API | Classification API | Distributed executor mp | Flash Attention 3 | FIA comparison | Chunked Prefill | Prefix Caching | CPU/KV offloading | KV transfer/events | Sleep/Wake memory | Xlite Graph | CP KV Interleave | Long Sequence | FlashComm1 env | Skipped | Conditional skip | Logprobs | Batch inference | Mixed lengths |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| multi_node/internal_dp/config/DeepSeek-V3.yaml | test DeepSeek-V3 disaggregated_prefill | vllm-ascend/DeepSeek-V3-W8A8 | | | ✅ | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | ✅ | ✅ | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | |
| multi_node/internal_dp/config/DeepSeek-V3_2-W8A8-EP_weekly.yaml | weekly test DeepSeek-V3.2-W8A8-EP disaggregated_prefill | vllm-ascend/DeepSeek-V3.2-W8A8 | | | ✅ | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | ✅ | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | | | | ✅ | | | | ✅ | | | | | | |
| multi_node/internal_dp/config/GLM-4.7-W8A8C8-Mooncake-Layerwise.yaml | test GLM-4.7-W8A8C8 PD separation with mooncake layerwise connector | vllm-ascend/GLM-4.7-W8A8C8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | ✅ | ✅ | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | | | | | |
| single_node/configs/DeepSeek-V3.2-W8A8_A3_weekly.yaml | DeepSeek-V3.2-W8A8-weekly | vllm-ascend/DeepSeek-V3.2-W8A8 | | | ✅ | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | |
| single_node/configs/GLM-5.yaml | GLM-5-TP16-DP1-decodegraph | Eco-Tech/GLM-5-w4a8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | ✅ | | | | | ✅ | | | | | | ✅ | ✅ | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/configs/GLM-5_1-W8A8_A3_weekly.yaml | GLM-5_1-w8a8-High—Throughput-bs10 | Eco-Tech/GLM-5.1-w8a8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | ✅ | | ✅ | | | | | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | ✅ | | | | | | | | | | | | | |
| single_node/configs/GLM-5_1-W8A8_A3_weekly.yaml | GLM-5_1-w8a8-High—Throughput-bs20 | Eco-Tech/GLM-5.1-w8a8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | ✅ | | ✅ | | | | | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | ✅ | | | | | | | | | | | | | |
| single_node/configs/GLM-5_1-W8A8_A3_weekly.yaml | GLM-5_1-w8a8-High—Throughput-bs32 | Eco-Tech/GLM-5.1-w8a8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | ✅ | | ✅ | | | | | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | ✅ | | | | | | | | | | | | | |
| single_node/configs/GLM-5_1-W8A8_A3_weekly.yaml | GLM-5_1-w8a8-High—Throughput-bs8 | Eco-Tech/GLM-5.1-w8a8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | ✅ | | ✅ | | | | | ✅ | | | | | | | ✅ | ✅ | | | | | | | | | | ✅ | | | | | | | | | | | | | |
| single_node/configs/Kimi-K2.5-32k-512.yaml | Kimi-K2.5-W4A8-TOPT20-32k-0.5k | Eco-Tech/Kimi-K2.5-W4A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Kimi-K2.5-32k-512.yaml | Kimi-K2.5-W4A8-TOPT20-32k-0.5k-pc90 | Eco-Tech/Kimi-K2.5-W4A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Kimi-K2.5-32k-512.yaml | Kimi-K2.5-W4A8-TOPT50-32k-0.5k | Eco-Tech/Kimi-K2.5-W4A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Kimi-K2.5-32k-512.yaml | Kimi-K2.5-W4A8-TOPT50-32k-0.5k-prefix-cache90 | Eco-Tech/Kimi-K2.5-W4A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Kimi-K2.5.yaml | Kimi-K2.5-W4A8-Case | Eco-Tech/Kimi-K2.5-W4A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Kimi-K2.5.yaml | Kimi-K2.5-W4A8-TOPT20-128k-1k-pc90 | Eco-Tech/Kimi-K2.5-W4A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Kimi-K2.5.yaml | Kimi-K2.5-W4A8-TOPT20-16k-1k | Eco-Tech/Kimi-K2.5-W4A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Kimi-K2.5.yaml | Kimi-K2.5-W4A8-TOPT20-64k-1k-pc90 | Eco-Tech/Kimi-K2.5-W4A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | | ✅ | | | | | | ✅ | | ✅ | | | | | | | | | | ✅ | | | | | | ✅ | ✅ | | | | | |
| single_node/configs/Kimi-K2.5.yaml | Kimi-K2.5-W4A8-TOPT50-128k-1k-pc90 | Eco-Tech/Kimi-K2.5-W4A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Kimi-K2.5.yaml | Kimi-K2.5-W4A8-TOPT50-16k-1k | Eco-Tech/Kimi-K2.5-W4A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Kimi-K2.5.yaml | Kimi-K2.5-W4A8-TOPT50-64k-1k-pc90 | Eco-Tech/Kimi-K2.5-W4A8 | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | | | | ✅ | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/MiniMax-M2.5-W8A8-A3.yaml | MiniMax-M2.5-w8a8 | Eco-Tech/MiniMax-M2.5-w8a8-QuaRot | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | |
| single_node/configs/MiniMax-M2.5-w8a8-QuaRot-A3.yaml | MiniMax-M2.5-w8a8 | Eco-Tech/MiniMax-M2.5-w8a8-QuaRot | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | |
| single_node/configs/MiniMax-M2.5-w8a8-QuaRot-A3.yaml | MiniMax-M2.5-w8a8-in128k-32-8 | Eco-Tech/MiniMax-M2.5-w8a8-QuaRot | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | ✅ | ✅ | | | | | |
| single_node/configs/MiniMax-M2.5-w8a8-QuaRot-A3.yaml | MiniMax-M2.5-w8a8-in128k-4-1 | Eco-Tech/MiniMax-M2.5-w8a8-QuaRot | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | ✅ | ✅ | | | | | |
| single_node/configs/MiniMax-M2.5-w8a8-QuaRot-A3.yaml | MiniMax-M2.5-w8a8-in128k-64-16 | Eco-Tech/MiniMax-M2.5-w8a8-QuaRot | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | ✅ | ✅ | | | | | |
| single_node/configs/MiniMax-M2.5-w8a8-QuaRot-A3.yaml | MiniMax-M2.5-w8a8-in16k-120-30 | Eco-Tech/MiniMax-M2.5-w8a8-QuaRot | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | |
| single_node/configs/MiniMax-M2.5-w8a8-QuaRot-A3.yaml | MiniMax-M2.5-w8a8-in16k-16-4 | Eco-Tech/MiniMax-M2.5-w8a8-QuaRot | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | |
| single_node/configs/MiniMax-M2.5-w8a8-QuaRot-A3.yaml | MiniMax-M2.5-w8a8-in32k-36-9 | Eco-Tech/MiniMax-M2.5-w8a8-QuaRot | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | |
| single_node/configs/MiniMax-M2.5-w8a8-QuaRot-A3.yaml | MiniMax-M2.5-w8a8-in32k-4-1 | Eco-Tech/MiniMax-M2.5-w8a8-QuaRot | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | |
| single_node/configs/MiniMax-M2.5-w8a8-QuaRot-A3.yaml | MiniMax-M2.5-w8a8-in32k-4-1-90 | Eco-Tech/MiniMax-M2.5-w8a8-QuaRot | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | ✅ | ✅ | | | | | |
| single_node/configs/MiniMax-M2.5-w8a8-QuaRot-A3.yaml | MiniMax-M2.5-w8a8-in32k-80-20 | Eco-Tech/MiniMax-M2.5-w8a8-QuaRot | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | ✅ | ✅ | | | | | |
| single_node/configs/MiniMax-M2.5-w8a8-QuaRot-A3.yaml | MiniMax-M2.5-w8a8-in64k-4-1 | Eco-Tech/MiniMax-M2.5-w8a8-QuaRot | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | ✅ | ✅ | | | | | |
| single_node/configs/MiniMax-M2.5-w8a8-QuaRot-A3.yaml | MiniMax-M2.5-w8a8-in64k-72-18 | Eco-Tech/MiniMax-M2.5-w8a8-QuaRot | | ✅ | | | | | | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | ✅ | ✅ | | | | | |
| single_node/configs/Qwen2.5-VL-7B-Instruct-EPD.yaml | Qwen2.5-VL-7B-Instruct-epd | Qwen/Qwen2.5-VL-7B-Instruct | | | | | | | | ✅ | | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/configs/Qwen3-32B.yaml | Qwen3-32B-TP4 | Qwen/Qwen3-32B | | ✅ | | | | | | | ✅ | | | | | | | | | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/configs/Qwen3.5-122B-A10B-W8A8-A2.yaml | Qwen3.5-122B-A10B-W8A8-single-A2 | Eco-Tech/Qwen3.5-122B-A10B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | ✅ | | | | | |
| single_node/configs/Qwen3.5-122B-A10B-W8A8-A3.yaml | Qwen3.5-122B-A10B-W8A8-A3 | Eco-Tech/Qwen3.5-122B-A10B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Qwen3.5-122B-A10B-W8A8-A3.yaml | Qwen3.5-122B-A10B-W8A8-TPOT20-16k-1k | Eco-Tech/Qwen3.5-122B-A10B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Qwen3.5-122B-A10B-W8A8-A3.yaml | Qwen3.5-122B-A10B-W8A8-TPOT20-32k-0.5k | Eco-Tech/Qwen3.5-122B-A10B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Qwen3.5-122B-A10B-W8A8-A3.yaml | Qwen3.5-122B-A10B-W8A8-TPOT20-64k-1k | Eco-Tech/Qwen3.5-122B-A10B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| single_node/configs/Qwen3.5-122B-A10B-W8A8-A3.yaml | Qwen3.5-122B-A10B-W8A8-TPOT50-16k-1k | Eco-Tech/Qwen3.5-122B-A10B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Qwen3.5-122B-A10B-W8A8-A3.yaml | Qwen3.5-122B-A10B-W8A8-TPOT50-32k-0.5k | Eco-Tech/Qwen3.5-122B-A10B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Qwen3.5-122B-A10B-W8A8-A3.yaml | Qwen3.5-122B-A10B-W8A8-TPOT50-64k-1k | Eco-Tech/Qwen3.5-122B-A10B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Qwen3.5-27B-w8a8-A3.yaml | Qwen3.5-27B-w8a8 | Eco-Tech/Qwen3.5-27B-w8a8-mtp | | | | | | | ✅ | | ✅ | | | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/configs/Qwen3.5-27B-w8a8-A3.yaml | Qwen3.5-27B-w8a8-in128k-28-7 | Eco-Tech/Qwen3.5-27B-w8a8-mtp | | | | | | | ✅ | | ✅ | | | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | ✅ | | | | | | |
| single_node/configs/Qwen3.5-27B-w8a8-A3.yaml | Qwen3.5-27B-w8a8-in128k-4-1 | Eco-Tech/Qwen3.5-27B-w8a8-mtp | | | | | | | ✅ | | ✅ | | | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | ✅ | | | | | | |
| single_node/configs/Qwen3.5-27B-w8a8-A3.yaml | Qwen3.5-27B-w8a8-in16k-16-4 | Eco-Tech/Qwen3.5-27B-w8a8-mtp | | | | | | | ✅ | | ✅ | | | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/configs/Qwen3.5-27B-w8a8-A3.yaml | Qwen3.5-27B-w8a8-in16k-56-14 | Eco-Tech/Qwen3.5-27B-w8a8-mtp | | | | | | | ✅ | | ✅ | | | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/configs/Qwen3.5-27B-w8a8-A3.yaml | Qwen3.5-27B-w8a8-in32k-16-4 | Eco-Tech/Qwen3.5-27B-w8a8-mtp | | | | | | | ✅ | | ✅ | | | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | ✅ | | | | | | |
| single_node/configs/Qwen3.5-27B-w8a8-A3.yaml | Qwen3.5-27B-w8a8-in32k-56-14 | Eco-Tech/Qwen3.5-27B-w8a8-mtp | | | | | | | ✅ | | ✅ | | | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | ✅ | | | | | | |
| single_node/configs/Qwen3.5-27B-w8a8-A3.yaml | Qwen3.5-27B-w8a8-in32k-8-2 | Eco-Tech/Qwen3.5-27B-w8a8-mtp | | | | | | | ✅ | | ✅ | | | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/configs/Qwen3.5-27B-w8a8-A3.yaml | Qwen3.5-27B-w8a8-in64k-16-4 | Eco-Tech/Qwen3.5-27B-w8a8-mtp | | | | | | | ✅ | | ✅ | | | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/configs/Qwen3.5-27B-w8a8-A3.yaml | Qwen3.5-27B-w8a8-in64k-48-12 | Eco-Tech/Qwen3.5-27B-w8a8-mtp | | | | | | | ✅ | | ✅ | | | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | ✅ | | | | | | |
| single_node/configs/Qwen3.5-27B-w8a8-A3.yaml | Qwen3.5-27B-w8a8-in64k-8-2 | Eco-Tech/Qwen3.5-27B-w8a8-mtp | | | | | | | ✅ | | ✅ | | | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/configs/Qwen3.5-27B-w8a8-A3.yaml | Qwen3.5-27B-w8a8-in64k-8-2-90 | Eco-Tech/Qwen3.5-27B-w8a8-mtp | | | | | | | ✅ | | ✅ | | | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | ✅ | | | | | | ✅ | | | | | | |
| single_node/configs/Qwen3.5-397B-A17B-W8A8-mtp-A3.yaml | Qwen3.5-397B-A17B-w8a8-mtp | Eco-Tech/Qwen3.5-397B-A17B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | ✅ | | | | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | | |
| single_node/configs/Qwen3.5-397B-A17B-W8A8-mtp-A3_weekly.yaml | Qwen3-397B-A17B-w8a8-A3-High—Throughput-bs136 | Eco-Tech/Qwen3.5-397B-A17B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Qwen3.5-397B-A17B-W8A8-mtp-A3_weekly.yaml | Qwen3-397B-A17B-w8a8-A3-High—Throughput-bs144 | Eco-Tech/Qwen3.5-397B-A17B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Qwen3.5-397B-A17B-W8A8-mtp-A3_weekly.yaml | Qwen3-397B-A17B-w8a8-A3-High—Throughput-bs32_in65536 | Eco-Tech/Qwen3.5-397B-A17B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Qwen3.5-397B-A17B-W8A8-mtp-A3_weekly.yaml | Qwen3-397B-A17B-w8a8-A3-High—Throughput-bs48 | Eco-Tech/Qwen3.5-397B-A17B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Qwen3.5-397B-A17B-W8A8-mtp-A3_weekly.yaml | Qwen3-397B-A17B-w8a8-A3-High—Throughput-bs8 | Eco-Tech/Qwen3.5-397B-A17B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Qwen3.5-397B-A17B-W8A8-mtp-A3_weekly.yaml | Qwen3-397B-A17B-w8a8-A3-High—Throughput-bs80 | Eco-Tech/Qwen3.5-397B-A17B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Qwen3.5-397B-A17B-W8A8-mtp-A3_weekly.yaml | Qwen3-397B-A17B-w8a8-A3-Minimal-Delay-bs16 | Eco-Tech/Qwen3.5-397B-A17B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Qwen3.5-397B-A17B-W8A8-mtp-A3_weekly.yaml | Qwen3-397B-A17B-w8a8-A3-Minimal-Delay-bs160 | Eco-Tech/Qwen3.5-397B-A17B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Qwen3.5-397B-A17B-W8A8-mtp-A3_weekly.yaml | Qwen3-397B-A17B-w8a8-A3-Minimal-Delay-bs16_in65536 | Eco-Tech/Qwen3.5-397B-A17B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Qwen3.5-397B-A17B-W8A8-mtp-A3_weekly.yaml | Qwen3-397B-A17B-w8a8-A3-Minimal-Delay-bs2 | Eco-Tech/Qwen3.5-397B-A17B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Qwen3.5-397B-A17B-W8A8-mtp-A3_weekly.yaml | Qwen3-397B-A17B-w8a8-A3-Minimal-Delay-bs32 | Eco-Tech/Qwen3.5-397B-A17B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
| single_node/configs/Qwen3.5-397B-A17B-W8A8-mtp-A3_weekly.yaml | Qwen3-397B-A17B-w8a8-A3-Minimal-Delay-bs36 | Eco-Tech/Qwen3.5-397B-A17B-w8a8-mtp | | | | | | | ✅ | | ✅ | | ✅ | | | | | | | | | | | ✅ | | ✅ | | | | | | | | | | | | | | | | | | | | | | | | | | ✅ | | | | | |
Reference in New Issue View Git Blame Copy Permalink