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

Simplify tests & Fix trtllm custom allreduce registration (#4252)

Browse Source
This commit is contained in:
Lianmin Zheng
2025-03-10 01:24:22 -07:00
committed by GitHub
parent 007f8b3dc2
commit aa957102a9
13 changed files with 30 additions and 211 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
test/srt/run_suite.py
View File

@@ -20,30 +20,33 @@ suites = {
TestFile("models/test_generation_models.py", 103),
TestFile("models/test_qwen_models.py", 82),
TestFile("models/test_reward_models.py", 83),
TestFile("test_gptqmodel_dynamic.py", 72),
TestFile("models/test_gme_qwen_models.py", 45),
TestFile("test_abort.py", 51),
TestFile("test_block_int8.py", 22),
TestFile("test_chunked_prefill.py", 336),
TestFile("test_custom_allreduce.py", 1),
TestFile("test_double_sparsity.py", 50),
TestFile("test_eagle_infer.py", 447),
TestFile("test_ebnf_constrained.py"),
TestFile("test_fp8_kernel.py", 2),
TestFile("test_embedding_openai_server.py", 36),
TestFile("test_eval_accuracy_mini.py", 63),
TestFile("test_gguf.py", 78),
TestFile("test_gptqmodel_dynamic.py", 72),
TestFile("test_hidden_states.py", 55),
TestFile("test_int8_kernel.py", 1),
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_deepseek_v3.py", 221),
TestFile("test_mla_flashinfer.py", 395),
TestFile("test_mla_fp8.py", 93),
TestFile("test_json_constrained.py", 98),
TestFile("test_large_max_new_tokens.py", 41),
TestFile("test_metrics.py", 32),
TestFile("test_no_chunked_prefill.py", 126),
TestFile("test_no_overlap_scheduler.py", 262),
TestFile("test_openai_server.py", 124),
TestFile("test_penalty.py", 41),
TestFile("test_pytorch_sampling_backend.py", 66),
TestFile("test_radix_attention.py", 167),
TestFile("test_reasoning_content.py", 89),
TestFile("test_regex_constrained.py", 64),
TestFile("test_release_memory_occupation.py", 44),
TestFile("test_request_length_validation.py", 31),
@@ -58,7 +61,6 @@ suites = {
TestFile("test_torchao.py", 70),
TestFile("test_triton_attention_kernels.py", 4),
TestFile("test_triton_attention_backend.py", 134),
TestFile("test_hidden_states.py", 55),
TestFile("test_update_weights_from_disk.py", 114),
TestFile("test_update_weights_from_tensor.py", 48),
TestFile("test_vertex_endpoint.py", 31),
@@ -66,10 +68,6 @@ suites = {
TestFile("test_vision_llm.py", 18.4),
TestFile("test_vision_openai_server.py", 344),
TestFile("test_w8a8_quantization.py", 46),
TestFile("test_fp8_kernel.py", 2),
TestFile("test_block_int8.py", 22),
TestFile("test_int8_kernel.py", 1),
TestFile("test_reasoning_content.py", 89),
],
"nightly": [
TestFile("test_nightly_gsm8k_eval.py"),