EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

[CI] Fix ci tests (#5769)

Browse Source
This commit is contained in:
Lianmin Zheng
2025-04-27 07:18:10 -07:00
committed by GitHub
parent 35ca04d2fa
commit 621e96bf9b
18 changed files with 126 additions and 295 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
test/srt/run_suite.py
View File

@@ -16,23 +16,29 @@ suites = {
TestFile("models/lora/test_lora.py", 76),
TestFile("models/lora/test_lora_backend.py", 99),
TestFile("models/lora/test_multi_lora_backend.py", 60),
TestFile("models/test_embedding_models.py", 35),
TestFile("models/test_embedding_models.py", 184),
TestFile("models/test_clip_models.py", 52),
TestFile("models/test_compressed_tensors_models.py", 42),
TestFile("models/test_generation_models.py", 103),
TestFile("models/test_gme_qwen_models.py", 45),
# TestFile("models/test_grok_models.py", 60), # Disabled due to illegal memory access
TestFile("models/test_qwen_models.py", 82),
TestFile("models/test_compressed_tensors_models.py", 100),
TestFile("models/test_reward_models.py", 83),
TestFile("models/test_gme_qwen_models.py", 45),
TestFile("models/test_clip_models.py", 52),
TestFile("models/test_vlm_models.py", 581),
TestFile("models/test_reward_models.py", 132),
TestFile("models/test_vlm_models.py", 317),
TestFile("test_abort.py", 51),
TestFile("test_block_int8.py", 22),
TestFile("test_create_kvindices.py", 2),
TestFile("test_chunked_prefill.py", 285),
TestFile("test_eagle_infer.py", 584),
TestFile("test_ebnf_constrained.py"),
TestFile("test_fa3.py", 376),
TestFile("test_fp8_kernel.py", 8),
TestFile("test_ebnf_constrained.py", 108),
TestFile("test_embedding_openai_server.py", 141),
TestFile("test_eval_fp8_accuracy.py", 303),
TestFile("test_fa3.py", 376),
TestFile("test_fim_completion.py", 40),
TestFile("test_fp8_kernel.py", 8),
TestFile("test_fused_moe.py", 30),
TestFile("test_hicache.py", 116),
TestFile("test_hicache_mla.py", 254),
TestFile("test_hidden_states.py", 55),
TestFile("test_int8_kernel.py", 8),
TestFile("test_input_embeddings.py", 38),
@@ -41,11 +47,11 @@ suites = {
TestFile("test_metrics.py", 32),
TestFile("test_mla.py", 242),
TestFile("test_mla_deepseek_v3.py", 221),
TestFile("test_mla_int8_deepseek_v3.py", 674),
TestFile("test_mla_int8_deepseek_v3.py", 389),
TestFile("test_mla_flashinfer.py", 395),
TestFile("test_mla_fp8.py", 153),
TestFile("test_no_chunked_prefill.py", 126),
TestFile("test_no_overlap_scheduler.py", 262),
TestFile("test_no_chunked_prefill.py", 108),
TestFile("test_no_overlap_scheduler.py", 216),
TestFile("test_openai_server.py", 149),
TestFile("test_penalty.py", 41),
TestFile("test_page_size.py", 60),
@@ -59,27 +65,21 @@ suites = {
TestFile("test_server_args.py", 1),
TestFile("test_skip_tokenizer_init.py", 117),
TestFile("test_srt_engine.py", 237),
TestFile("test_srt_endpoint.py", 94),
TestFile("test_srt_endpoint.py", 130),
TestFile("test_torch_compile.py", 76),
TestFile("test_torch_compile_moe.py", 235),
TestFile("test_torch_compile_moe.py", 172),
TestFile("test_torch_native_attention_backend.py", 123),
TestFile("test_torchao.py", 70),
TestFile("test_triton_attention_kernels.py", 4),
TestFile("test_triton_attention_backend.py", 134),
TestFile("test_triton_moe_channel_fp8_kernel.py", 25),
TestFile("test_update_weights_from_disk.py", 114),
TestFile("test_update_weights_from_tensor.py", 48),
TestFile("test_vertex_endpoint.py", 31),
TestFile("test_vision_chunked_prefill.py", 119),
TestFile("test_vision_chunked_prefill.py", 175),
TestFile("test_vlm_accuracy.py", 60),
TestFile("test_vision_openai_server.py", 637),
TestFile("test_fim_completion.py", 40),
TestFile("test_w8a8_quantization.py", 46),
TestFile("test_eval_fp8_accuracy.py", 303),
TestFile("test_create_kvindices.py", 2),
TestFile("test_hicache.py", 116),
TestFile("test_hicache_mla.py", 254),
TestFile("test_fused_moe.py", 30),
TestFile("test_triton_moe_channel_fp8_kernel.py", 25),
],
"per-commit-2-gpu": [
TestFile("models/lora/test_lora_tp.py", 116),