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

Fix 2-gpu CI test and suppress some warnings (#4930)

Browse Source
This commit is contained in:
Lianmin Zheng
2025-03-30 12:51:44 -07:00
committed by GitHub
parent f842853a40
commit 9adf178cc2
4 changed files with 21 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
test/srt/run_suite.py
View File

@@ -15,7 +15,7 @@ suites = {
"per-commit": [
TestFile("models/lora/test_lora.py", 76),
TestFile("models/lora/test_lora_backend.py", 420),
TestFile("models/lora/test_multi_lora_backend.py", 144),
TestFile("models/lora/test_multi_lora_backend.py", 60),
TestFile("models/test_embedding_models.py", 35),
TestFile("models/test_generation_models.py", 103),
TestFile("models/test_grok_models.py", 60),
@@ -28,15 +28,15 @@ suites = {
TestFile("test_chunked_prefill.py", 336),
TestFile("test_eagle_infer.py", 500),
TestFile("test_ebnf_constrained.py"),
TestFile("test_fp8_kernel.py", 2),
TestFile("test_fp8_kernel.py", 8),
TestFile("test_embedding_openai_server.py", 36),
TestFile("test_hidden_states.py", 55),
TestFile("test_int8_kernel.py", 1),
TestFile("test_int8_kernel.py", 8),
TestFile("test_input_embeddings.py", 38),
TestFile("test_json_constrained.py", 98),
TestFile("test_large_max_new_tokens.py", 41),
TestFile("test_metrics.py", 32),
TestFile("test_mla.py", 92),
TestFile("test_mla.py", 162),
TestFile("test_mla_deepseek_v3.py", 221),
TestFile("test_mla_int8_deepseek_v3.py", 522),
TestFile("test_mla_flashinfer.py", 395),
@@ -68,23 +68,23 @@ suites = {
TestFile("test_vertex_endpoint.py", 31),
TestFile("test_vision_chunked_prefill.py", 223),
TestFile("test_vlm_accuracy.py", 60),
TestFile("test_vision_openai_server.py", 344),
TestFile("test_fim_completion.py", 120),
TestFile("test_vision_openai_server.py", 537),
TestFile("test_fim_completion.py", 40),
TestFile("test_w8a8_quantization.py", 46),
TestFile("test_eval_fp8_accuracy.py", 172),
TestFile("test_eval_fp8_accuracy.py", 303),
TestFile("test_create_kvindices.py", 2),
TestFile("test_hicache.py", 60),
TestFile("test_hicache_mla.py", 90),
],
"per-commit-2-gpu": [
TestFile("models/lora/test_lora_tp.py", 300),
TestFile("test_data_parallelism.py", 90),
TestFile("test_dp_attention.py", 90),
TestFile("test_mla_tp.py", 420),
TestFile("test_moe_ep.py", 220),
TestFile("test_patch_torch.py", 30),
TestFile("test_update_weights_from_distributed.py", 100),
TestFile("test_verl_engine.py", 100),
TestFile("test_patch_torch.py", 30),
TestFile("test_moe_ep.py", 220),
TestFile("test_mla_tp.py", 420),
TestFile("test_lora_tp.py", 300),
],
"nightly": [
TestFile("test_nightly_gsm8k_eval.py"),