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

[AMD] Expand test coverage for AMD CI and enable apply_token_bitmask_inplace_cuda in sgl-kernel (#8268)

Browse Source
This commit is contained in:
Hubert Lu
2025-08-15 12:32:51 -07:00
committed by GitHub
parent e52c3866eb
commit 9c3e95d98b
6 changed files with 61 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
test/srt/run_suite.py
View File

@@ -158,40 +158,66 @@ suites = {
# Add AMD tests
suite_amd = {
"per-commit-amd": [
TestFile("lora/test_lora.py", 200),
TestFile("lora/test_lora_eviction.py", 200),
TestFile("lora/test_lora_backend.py", 99),
TestFile("lora/test_multi_lora_backend.py", 60),
TestFile("lora/test_lora_cuda_graph.py", 250),
TestFile("lora/test_lora_qwen3.py", 97),
TestFile("models/test_embedding_models.py", 73),
TestFile("models/test_compressed_tensors_models.py", 42),
TestFile("models/test_qwen_models.py", 82),
TestFile("models/test_reward_models.py", 132),
TestFile("models/test_transformers_models.py", 320),
TestFile("openai_server/basic/test_protocol.py", 10),
TestFile("openai_server/basic/test_serving_chat.py", 10),
TestFile("openai_server/basic/test_serving_completions.py", 10),
TestFile("openai_server/basic/test_serving_embedding.py", 10),
TestFile("openai_server/basic/test_openai_embedding.py", 141),
TestFile("openai_server/basic/test_openai_server.py", 149),
TestFile("openai_server/features/test_enable_thinking.py", 70),
TestFile("openai_server/features/test_json_constrained.py", 98),
TestFile("openai_server/features/test_json_mode.py", 90),
TestFile("openai_server/features/test_openai_server_ebnf.py", 95),
# TestFile("openai_server/features/test_openai_server_hidden_states.py", 240),
TestFile("openai_server/features/test_reasoning_content.py", 89),
TestFile("openai_server/function_call/test_openai_function_calling.py", 60),
TestFile("openai_server/function_call/test_tool_choice.py", 226),
TestFile("openai_server/validation/test_large_max_new_tokens.py", 41),
TestFile("openai_server/validation/test_matched_stop.py", 60),
TestFile("openai_server/validation/test_openai_server_ignore_eos.py", 85),
TestFile("openai_server/validation/test_request_length_validation.py", 31),
TestFile("quant/test_block_int8.py", 22),
TestFile("quant/test_awq_dequant.py", 2),
TestFile("rl/test_update_weights_from_disk.py", 114),
# TestFile("rl/test_update_weights_from_tensor.py", 48),
TestFile("test_abort.py", 51),
TestFile("test_create_kvindices.py", 2),
TestFile("test_chunked_prefill.py", 313),
TestFile("test_ebnf_constrained.py", 108),
TestFile("test_eval_fp8_accuracy.py", 303),
TestFile("test_function_call_parser.py", 10),
TestFile("test_fused_moe.py", 30),
TestFile("test_input_embeddings.py", 38),
TestFile("test_io_struct.py", 8),
TestFile("test_jinja_template_utils.py", 1),
TestFile("test_metrics.py", 32),
TestFile("test_mla.py", 242),
TestFile("test_mla_deepseek_v3.py", 221),
TestFile("test_metrics.py", 32),
TestFile("test_no_chunked_prefill.py", 108),
# TestFile("test_no_overlap_scheduler.py", 234), # Disabled temporarily and track in #7703
TestFile("test_penalty.py", 41),
TestFile("test_page_size.py", 60),
TestFile("test_pytorch_sampling_backend.py", 66),
TestFile("test_radix_attention.py", 105),
TestFile("test_regex_constrained.py", 64),
TestFile("test_retract_decode.py", 54),
TestFile("test_reasoning_parser.py", 5),
TestFile("test_rope_rocm.py", 3),
TestFile("test_server_args.py", 1),
TestFile("test_skip_tokenizer_init.py", 117),
TestFile("test_srt_engine.py", 261),
TestFile("test_srt_endpoint.py", 130),
TestFile("test_torch_compile.py", 76),
TestFile("test_torch_compile_moe.py", 172),
TestFile("test_torch_native_attention_backend.py", 123),