EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity
Files
ae523675e547009d3c09bd0220944ca542bda3cb
sglang/test/srt
History
Qiaolin Yu 8c0cfca87d Feat: support cuda graph for LoRA (#4115) 
Co-authored-by: Beichen Ma <mabeichen12@gmail.com>
2025-04-28 23:30:44 -07:00
..
configs
Add test config yamls for Deepseek v3 (#5433)
2025-04-20 17:28:52 -07:00
models
Feat: support cuda graph for LoRA (#4115)
2025-04-28 23:30:44 -07:00
double-sparsity-config-Llama-3.1-8B-Instruct.json
Rename double sparsity config file (#2188)
2024-11-25 17:12:08 -08:00
experiment_runner.py
feat: update experiment_runner (#5360)
2025-04-13 15:37:05 -07:00
kv_cache_scales_llama3_1_8b.json
Support FP8 E4M3 KV Cache (#2786)
2025-01-12 21:17:11 -08:00
kv_cache_scales_llama3_8b.json
support e4m3 kvcache in qwen2 & add kv scaling facotr json (#2894)
2025-01-18 11:43:22 +08:00
kv_cache_scales_qwen2_1_5b.json
support e4m3 kvcache in qwen2 & add kv scaling facotr json (#2894)
2025-01-18 11:43:22 +08:00
parse_results.py
Add test config yamls for Deepseek v3 (#5433)
2025-04-20 17:28:52 -07:00
run_suite.py
Feat: support cuda graph for LoRA (#4115)
2025-04-28 23:30:44 -07:00
test_abort.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_awq.py
Fix CI tests (#4853)
2025-03-28 00:28:35 -07:00
test_bench_one_batch.py
[CI] test chunked prefill more (#5798)
2025-04-28 10:57:17 -07:00
test_bench_serving.py
[CI] Improve github summary & enable fa3 for more models (#5796)
2025-04-27 15:29:46 -07:00
test_block_int8.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_bnb.py
Support BNB quantization for llama/mllama (#5038)
2025-04-15 18:00:31 -07:00
test_cache_report.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_chunked_prefill.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_create_kvindices.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_custom_allreduce.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_data_parallelism.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_double_sparsity.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_dp_attention.py
Fix DeepSeek DP Attention + torch compile (#5367)
2025-04-14 01:07:58 -07:00
test_eagle_infer.py
Fix eagle test case (#5776)
2025-04-27 01:00:54 -07:00
test_ebnf_constrained.py
update llguidance to 0.7.11; adds StructTag (#4870)
2025-04-26 20:13:57 -07:00
test_embedding_openai_server.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_eval_accuracy_large.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_eval_fp8_accuracy.py
[CI] Fix ci tests (#5769)
2025-04-27 07:18:10 -07:00
test_expert_distribution.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_fa3.py
[CI] Fix ci tests (#5769)
2025-04-27 07:18:10 -07:00
test_fim_completion.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_fp8_kernel.py
Clean up imports (#5467)
2025-04-16 15:26:49 -07:00
test_fp8_kvcache.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_full_deepseek_v3.py
[CI] tune the test order to warmup the server (#5860)
2025-04-28 19:27:37 -07:00
test_function_calling.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_fused_moe.py
[ci] fix ci test fused_moe op (#5102)
2025-04-09 08:52:46 -07:00
test_get_weights_by_name.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_gguf.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_gptqmodel_dynamic.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_health_check.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_hicache_mla.py
upstream hicache fixes (#5570)
2025-04-20 23:08:30 -07:00
test_hicache_page.py
upstream hicache fixes (#5570)
2025-04-20 23:08:30 -07:00
test_hicache.py
upstream hicache fixes (#5570)
2025-04-20 23:08:30 -07:00
test_hidden_states.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_input_embeddings.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_int8_kernel.py
Support Llama4 fp8 inference (#5194)
2025-04-09 20:14:34 +08:00
test_io_struct.py
[feat&refactor] Enhance multimodal input support with refactor io_struct (#4938)
2025-04-08 14:48:07 -07:00
test_json_constrained.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_json_mode.py
Feat: Implement JSON Mode (response_format.type="json_object") (#4733)
2025-04-20 17:41:22 -07:00
test_large_max_new_tokens.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_local_attn.py
Simplify FA3 tests (#5779)
2025-04-27 01:30:17 -07:00
test_matched_stop.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_metrics.py
Fix retract for page size > 1 (#4914)
2025-03-30 02:57:15 -07:00
test_mla_deepseek_v3.py
[CI] test chunked prefill more (#5798)
2025-04-28 10:57:17 -07:00
test_mla_flashinfer.py
[Revision] Replace enable_flashinfer_mla argument with attention_backend (#5052)
2025-04-05 01:23:02 -07:00
test_mla_fp8.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_mla_int8_deepseek_v3.py
Warn users when release_memory_occupation is called without memory saver enabled (#4566)
2025-03-26 00:18:14 -07:00
test_mla_tp.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_mla.py
[CI] test chunked prefill more (#5798)
2025-04-28 10:57:17 -07:00
test_modelopt_fp8kvcache.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_modelopt.py
[CI] Fix ci tests (#5769)
2025-04-27 07:18:10 -07:00
test_models_from_modelscope.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_moe_deepep.py
Support (1 <= dp < tp) in the dp attention in DeepEP (#4770)
2025-03-27 17:09:35 -07:00
test_moe_ep.py
[misc] fix ci flaky case (#5352)
2025-04-15 01:37:16 -07:00
test_moe_eval_accuracy_large.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_nightly_gsm8k_eval.py
[CI] Fix ci tests (#5769)
2025-04-27 07:18:10 -07:00
test_no_chunked_prefill.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_no_overlap_scheduler.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_openai_server.py
[Feature] Prefill assistant response - add continue_final_message parameter (#4226)
2025-04-20 17:37:18 -07:00
test_page_size.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_patch_torch.py
Patch PyTorch's bug that cross-process tensor transfer will lead to wrong device (#4565)
2025-03-27 00:22:33 -07:00
test_penalty.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_pytorch_sampling_backend.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_radix_attention.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_reasoning_content.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_regex_constrained.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_release_memory_occupation.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_request_length_validation.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_retract_decode.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_sagemaker_server.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_schedule_policy.py
Fix missing arguments in SchedulePolicy and RadixCache initialization in tests. (#4712)
2025-03-27 22:23:51 -07:00
test_server_args.py
Fix CI tests (#4853)
2025-03-28 00:28:35 -07:00
test_session_control.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_skip_tokenizer_init.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_srt_endpoint.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_srt_engine_with_quant_args.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_srt_engine.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_torch_compile_moe.py
[CI] fix port conflicts (#5789)
2025-04-27 05:17:44 -07:00
test_torch_compile.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_torch_native_attention_backend.py
[CI] test chunked prefill more (#5798)
2025-04-28 10:57:17 -07:00
test_torch_tp.py
[CI] test chunked prefill more (#5798)
2025-04-28 10:57:17 -07:00
test_torchao.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_triton_attention_backend.py
[CI] test chunked prefill more (#5798)
2025-04-28 10:57:17 -07:00
test_triton_attention_kernels.py
Feat/support encoder model (like bert) (#4887)
2025-04-17 01:50:48 -07:00
test_triton_attention_rocm_mla.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_triton_moe_channel_fp8_kernel.py
Clean up imports (#5467)
2025-04-16 15:26:49 -07:00
test_triton_moe_wna16.py
[2/3] fix dsv3 awq issue (#4625)
2025-04-03 17:36:39 -07:00
test_update_weights_from_disk.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_update_weights_from_distributed.py
[CI] fix port conflicts (#5789)
2025-04-27 05:17:44 -07:00
test_update_weights_from_tensor.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_verl_engine_server.py
Support server based rollout in Verlengine (#4848)
2025-04-12 10:07:52 -07:00
test_verl_engine.py
Support server based rollout in Verlengine (#4848)
2025-04-12 10:07:52 -07:00
test_vertex_endpoint.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_vision_chunked_prefill.py
CI: rewrite test_vision_chunked_prefill to speedup (#5682)
2025-04-26 18:33:13 -07:00
test_vision_openai_server.py
[Feature] support auto chat template (#4949)
2025-04-28 22:34:18 -07:00
test_vllm_dependency.py
Adjust ci test threshold (#5271)
2025-04-11 22:03:37 -07:00
test_vlm_accuracy.py
vlm: enable radix cache for qwen-vl models (#5349)
2025-04-23 20:35:05 -07:00
test_w8a8_quantization.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00