chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity
Files
061f41affc703abc6c93958f4e04a93e946e299d
sglang/test/srt
History
SeanWeiSean 7759716786 bugfix[schedule]: Refactor sort method and add related UT (#13576) 
Co-authored-by: Yuxuan Wei <w1300012920@pku.edu.cn>
Co-authored-by: Yuxuan Wei <w1300012920@gmail.com>
Co-authored-by: Yuxuan Wei🚚 <yuxwei@microsoft.com>
2025-12-23 03:13:57 +08:00
..
ascend
[Feature] npu support enable_torch_compile for torchair backend (#13410)
2025-12-16 09:23:51 +08:00
configs
Add test config yamls for Deepseek v3 (#5433)
2025-04-20 17:28:52 -07:00
cpu
[CPU] Add 4D input support for ROPE in sgl-kernel (#9337)
2025-12-16 17:27:39 +08:00
debug_utils
Test reorganization: Move tests to manual/ (#13610)
2025-11-20 13:41:58 -08:00
dllm
[DLLM] Fix dLLM regression (#15371)
2025-12-19 10:55:46 +08:00
ep
fix ds3.2 nsa backend prefill TBO (#14901)
2025-12-21 13:16:46 -08:00
external_models
feat: support external custom models (#13429)
2025-11-20 11:16:58 +08:00
hicache
Revert "tiny remove deprecated endpoint call" (#14533)
2025-12-05 23:48:54 -08:00
layers/attention/mamba
[CI] Move nightly tests to test/nightly/ (#13683)
2025-11-20 18:00:02 -08:00
models
Adapt fixture-kit to gsm8k mixin (#15599)
2025-12-22 14:19:35 +08:00
nightly
[AMD] Add TP=8 models to nightly test and make TP=2 test stable (#15296)
2025-12-19 13:15:19 -08:00
openai_server
Clean up __init__ function of the scheduler and event loop for PD (#15298)
2025-12-18 01:35:14 -08:00
ops
[VLM] Replace torch.repeat_interleave with faster np.repeat for Qwen-VL series (#13736)
2025-11-22 22:45:32 +08:00
quant
[kernel][moe] add moe topk fast (#13969)
2025-12-14 22:26:40 +08:00
rl
[Feature] Enable return routed experts (#12162)
2025-12-21 15:16:43 +08:00
rotary_embedding
fix: small changes to enable test_mrope.py (#14082)
2025-11-27 22:58:17 -08:00
xpu
Extend lint test to test/ directory (#13247)
2025-11-14 00:01:48 -08:00
double-sparsity-config-Llama-3.1-8B-Instruct.json
…
experiment_runner.py
Extend lint test to test/ directory (#13247)
2025-11-14 00:01:48 -08:00
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
misc: parse bench_serving result as markdown table (#9377)
2025-08-20 16:44:20 -07:00
run_suite.py
bugfix[schedule]: Refactor sort method and add related UT (#13576)
2025-12-23 03:13:57 +08:00
test_abort.py
Extend lint test to test/ directory (#13247)
2025-11-14 00:01:48 -08:00
test_bench_one_batch.py
Extend lint test to test/ directory (#13247)
2025-11-14 00:01:48 -08:00
test_bench_serving.py
[Embeddings Performance Testing] Add performance test for embedding models (#12359)
2025-11-17 15:35:18 -08:00
test_bench_typebaseddispatcher.py
perf: optimize TypeBasedDispatcher using dict for O(1) lookup (#12001)
2025-11-15 22:02:42 +08:00
test_bnb.py
Extend lint test to test/ directory (#13247)
2025-11-14 00:01:48 -08:00
test_chunked_prefill.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_constrained_decoding_spec_reasoning.py
Support grammar + spec + reasoning (#14163)
2025-11-30 21:19:57 +08:00
test_constrained_decoding.py
[Test] Merge all constrained decoding tests. (#12633)
2025-11-05 00:43:06 +08:00
test_create_kvindices.py
Extend lint test to test/ directory (#13247)
2025-11-14 00:01:48 -08:00
test_cutedsl_moe.py
Replace [silu_and_mul_]scaled_fp4_group_quant by Flashinfer equivalent (#12376)
2025-11-13 00:26:00 -08:00
test_data_parallelism.py
Revert "tiny remove deprecated endpoint call" (#14533)
2025-12-05 23:48:54 -08:00
test_deepseek_v3_basic.py
Extend lint test to test/ directory (#13247)
2025-11-14 00:01:48 -08:00
test_deepseek_v3_cutedsl_4gpu.py
[CI]Add gb200 runner back (#15024)
2025-12-12 20:19:34 -08:00
test_deepseek_v3_fp4_4gpu.py
[Tiny]Move deepseek fp4 cutlass moe test to per-commit test (#15565)
2025-12-21 18:08:07 -08:00
test_deepseek_v3_mtp.py
[AMD] add unit-test-backend-8-gpu-amd back (#15253)
2025-12-19 00:59:28 -08:00
test_deepseek_v32_basic.py
[Deepseek V3.2] Fix accuracy bug in the Indexer (#12583)
2025-11-11 16:15:26 -08:00
test_deepseek_v32_mtp.py
Revert "tiny remove deprecated endpoint call" (#14533)
2025-12-05 23:48:54 -08:00
test_deterministic.py
Extend lint test to test/ directory (#13247)
2025-11-14 00:01:48 -08:00
test_disaggregation_basic.py
Introduce server_fixtures in sglang.test (#14899)
2025-12-11 22:30:33 +09:00
test_disaggregation_different_tp.py
Introduce server_fixtures in sglang.test (#14899)
2025-12-11 22:30:33 +09:00
test_disaggregation_dp_attention.py
Introduce server_fixtures in sglang.test (#14899)
2025-12-11 22:30:33 +09:00
test_disaggregation_hybrid_attention.py
[Qwen3-next] Add PD disaggregation support for mamba with extra_buffer (#15180)
2025-12-16 14:36:00 +08:00
test_disaggregation_pp.py
[PP] Add dynamic chunking PP test (#15395)
2025-12-19 01:09:40 +08:00
test_dp_attention.py
Revert "tiny remove deprecated endpoint call" (#14533)
2025-12-05 23:48:54 -08:00
test_eagle_dp_attention.py
Revert "tiny remove deprecated endpoint call" (#14533)
2025-12-05 23:48:54 -08:00
test_eagle_infer_beta_dp_attention.py
[CI] fix UT success check in test_eagle_infer_beta_dp_attention.py (#14831)
2025-12-11 01:00:50 +09:00
test_epd_disaggregation.py
fix: moving decorator to header (#15297)
2025-12-16 17:05:45 -08:00
test_eval_accuracy_large.py
Extend lint test to test/ directory (#13247)
2025-11-14 00:01:48 -08:00
test_eval_fp8_accuracy.py
[CI] Fix ci tests (#5769)
2025-04-27 07:18:10 -07:00
test_external_models.py
tiny unify environ usage (#15335)
2025-12-17 23:31:43 +08:00
test_fa3.py
Revert "tiny remove deprecated endpoint call" (#14533)
2025-12-05 23:48:54 -08:00
test_flash_attention_4.py
fix b200 fa4 ci (#14788)
2025-12-10 00:03:43 -08:00
test_flashmla.py
Reserve more memory for DeepSeekOCR model and adjust server start timeout for DeepGEMM to reduce flakiness (#15277)
2025-12-17 13:13:05 -08:00
test_fp8_blockwise_gemm.py
Add FP8 Blockwise GEMM Backend Flag --fp8-gemm-backend (#14379)
2025-12-09 12:05:56 -08:00
test_fp8_utils.py
Support inverse transform ue8m0 scale (#13285)
2025-11-15 16:34:32 +08:00
test_fused_moe.py
Extend lint test to test/ directory (#13247)
2025-11-14 00:01:48 -08:00
test_gguf.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_gpt_oss_1gpu.py
Fix CI (#9013)
2025-08-09 16:00:10 -07:00
test_gpt_oss_4gpu.py
feat: add gpt oss b200 ci (#9988)
2025-09-03 17:26:38 -07:00
test_gpt_oss_common.py
Fix condition for streaming output_ids in tokenizer manager (#13759)
2025-11-29 13:56:15 -08:00
test_gptqmodel_dynamic.py
Depreate global_server_args_dict (#11528)
2025-10-13 19:34:43 +08:00
test_harmony_parser.py
Move parsers under a single folder (#9912)
2025-09-02 18:25:04 -07:00
test_hidden_states.py
Open AI API hidden states (#6716)
2025-06-10 14:37:29 -07:00
test_hybrid_attn_backend.py
Revert "tiny remove deprecated endpoint call" (#14533)
2025-12-05 23:48:54 -08:00
test_input_embeddings.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_io_struct.py
fix: Handles input_embeds in GenerateReqInput when n>1 (#7830)
2025-07-08 14:00:42 -07:00
test_jinja_template_utils.py
Move parsers under a single folder (#9912)
2025-09-02 18:25:04 -07:00
test_llama31_fp4.py
fix b200 ci (#14786)
2025-12-09 23:08:41 -08:00
test_load_weights_from_remote_instance.py
support non disturbing remote instance weight loader v2 (#14997)
2025-12-16 14:39:56 -08:00
test_local_attn.py
Simplify FA3 tests (#5779)
2025-04-27 01:30:17 -07:00
test_mamba_unittest.py
[Qwen3-next] support mamba radix cache for overlap scheduler (#14792)
2025-12-14 18:54:16 -08:00
test_metrics_utils.py
Rename customer label -> custom label (#10899)
2025-09-25 16:19:53 -07:00
test_metrics.py
Improve structured outputs: fix race condition, server crash, metrics and style (#6188)
2025-05-11 08:36:16 -07:00
test_mistral_large3_basic.py
Add nightly accuracy test for DeepSeek V3.2 (#14935)
2025-12-13 12:11:16 -08:00
test_mla_deepseek_v3.py
Increase timeout for TestDeepseekV3MTP for potential DeepGEMM cold start (#15239)
2025-12-16 00:26:10 -08:00
test_mla_flashinfer.py
Revert "tiny remove deprecated endpoint call" (#14533)
2025-12-05 23:48:54 -08:00
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
Revert "tiny remove deprecated endpoint call" (#14533)
2025-12-05 23:48:54 -08:00
test_mla.py
Improve profiler and integrate profiler in bench_one_batch_server (#6787)
2025-05-31 15:53:55 -07:00
test_model_hooks.py
Rename: --hooks to --forward-hooks (#13994)
2025-11-26 22:26:28 +08:00
test_modelopt_export.py
Extend lint test to test/ directory (#13247)
2025-11-14 00:01:48 -08:00
test_modelopt_loader.py
Extend lint test to test/ directory (#13247)
2025-11-14 00:01:48 -08:00
test_moe_eval_accuracy_large.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_multi_instance_release_memory_occupation.py
Fix mem fraction static for nightly tests (#11076)
2025-09-29 12:57:41 -07:00
test_multi_tokenizer.py
Extend lint test to test/ directory (#13247)
2025-11-14 00:01:48 -08:00
test_ngram_speculative_decoding.py
Revert "tiny remove deprecated endpoint call" (#14533)
2025-12-05 23:48:54 -08:00
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_original_logprobs.py
Extend lint test to test/ directory (#13247)
2025-11-14 00:01:48 -08:00
test_page_size.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_patch_torch.py
Tiny move files to utils folder (#11166)
2025-10-03 22:40:06 +08:00
test_penalty.py
[Test] Add Functional Tests for Penalty Parameters (#11931)
2025-11-01 00:10:17 +08:00
test_pp_single_node.py
[PP] Add pp support for Qwen3-VL (#12333)
2025-12-17 16:03:58 +08:00
test_prefill_adder.py
bugfix[schedule]: Refactor sort method and add related UT (#13576)
2025-12-23 03:13:57 +08:00
test_priority_scheduling.py
[Fix]: Adjust FutureMap's token_id_bufs Size to Prevent ChunkedPrefill's next_token_ids from Overwriting Previous Prefill Requests' next_token_id (#13713)
2025-11-25 01:08:52 +08:00
test_profile_merger_http_api.py
[FEATURE] Add Profile Trace Merger for Distributed Traces (#11413)
2025-10-14 09:20:17 +08:00
test_profile_merger.py
[FEATURE] Add Profile Trace Merger for Distributed Traces (#11413)
2025-10-14 09:20:17 +08:00
test_profile_v2.py
Implement profiler v2 and fix stage mixture bug (#14148)
2025-11-30 16:59:52 +08:00
test_pytorch_sampling_backend.py
Add retry for flaky tests in CI (#4755)
2025-03-25 16:53:12 -07:00
test_quantization.py
Fix import warnings (#15144)
2025-12-14 21:25:18 -08:00
test_radix_attention.py
Enhance runtime memory check in CI (#15192)
2025-12-16 21:40:38 +08:00
test_radix_cache_unit.py
fix: malformed KV events for NVIDIA Dynamo (#13488)
2025-11-28 14:55:20 -08:00
test_reasoning_parser.py
Move parsers under a single folder (#9912)
2025-09-02 18:25:04 -07:00
test_release_memory_occupation.py
Support releasing CUDA graph memory when paused (#7873)
2025-10-28 14:40:50 +08:00
test_request_queue_validation.py
Simplify the BatchMultimodalOutput in io_struct.py (#12993)
2025-11-10 13:54:56 -08:00
test_retract_decode.py
Enhance runtime memory check in CI (#15192)
2025-12-16 21:40:38 +08:00
test_rope_rocm.py
[AMD] Clear pre-built AITER kernels and warmup to prevent segfaults and test timeouts (#15318)
2025-12-18 14:00:09 -08:00
test_score_api.py
[Generative Score API] Multi-Item scoring with custom attention mask. (#10979)
2025-10-08 18:47:32 -07:00
test_server_args.py
Do not use MagicMock to mock server_args in tests (#12154)
2025-10-26 16:00:46 +08:00
test_skip_tokenizer_init.py
[CI fix] Fix image download failures in VLM CI tests (#13613)
2025-11-20 11:18:06 +08:00
test_soft_watchdog.py
Tiny add stuck simulation (#15613)
2025-12-22 17:00:18 +08:00
test_speculative_registry.py
[Auto Sync] Update scheduler.py, spec_info.py, run_suite.py... (20251027) (#12235)
2025-10-27 17:21:08 -07:00
test_srt_endpoint.py
Revert "tiny remove deprecated endpoint call" (#14533)
2025-12-05 23:48:54 -08:00
test_srt_engine.py
Tiny move files to utils folder (#11166)
2025-10-03 22:40:06 +08:00
test_standalone_speculative_decoding.py
Revert "tiny remove deprecated endpoint call" (#14533)
2025-12-05 23:48:54 -08:00
test_start_profile.py
[feature] Add layerwise NVTX support (#11870)
2025-11-15 19:20:56 -08:00
test_swa_unittest.py
Refactor cache init logic (#13800)
2025-11-24 11:41:46 +08:00
test_torch_compile_moe.py
[UT for RL] Add UT to cover release/resume memory case for moe model (#8803)
2025-09-09 19:25:12 -07:00
test_torch_compile.py
Improve profiler and integrate profiler in bench_one_batch_server (#6787)
2025-05-31 15:53:55 -07:00
test_torch_native_attention_backend.py
[CI] test chunked prefill more (#5798)
2025-04-28 10:57:17 -07:00
test_torchao.py
Fix TorchAO quant in VLM (#13508)
2025-11-24 22:15:40 +08:00
test_triton_attention_backend.py
[CI] test chunked prefill more (#5798)
2025-04-28 10:57:17 -07:00
test_triton_attention_kernels.py
fixes hardcoded "cuda" device references in unit tests to use a dynamic device selection (#12761)
2025-11-07 11:38:35 +08:00
test_triton_fused_moe.py
Fix B200 Nightly tests and move one manual test back to unit test to prevent the same issue (#13746)
2025-11-21 17:41:12 -08:00
test_triton_moe_channel_fp8_kernel.py
Support true on-policy (#12058)
2025-10-25 10:23:42 +08:00
test_triton_sliding_window.py
Fix triton sliding window test case (#6981)
2025-06-08 17:20:46 -07:00
test_type_based_dispatcher.py
perf: optimize TypeBasedDispatcher using dict for O(1) lookup (#12001)
2025-11-15 22:02:42 +08:00
test_utils_update_weights.py
Fix CI (#9012)
2025-08-09 13:33:42 -07:00
test_video_utils.py
Support nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 (and nvidia/C-RADIOv2-H) (#12277)
2025-11-26 16:28:52 -07:00
test_vision_chunked_prefill.py
Increase timeout for TestDeepseekV3MTP for potential DeepGEMM cold start (#15239)
2025-12-16 00:26:10 -08:00
test_vision_openai_server_a.py
vlm: refactor engine vlm params and support processor output as input (#14091)
2025-12-20 18:31:24 +08:00
test_vision_openai_server_common.py
Reserve more memory for DeepSeekOCR model and adjust server start timeout for DeepGEMM to reduce flakiness (#15277)
2025-12-17 13:13:05 -08:00
test_vlm_input_format.py
vlm: refactor engine vlm params and support processor output as input (#14091)
2025-12-20 18:31:24 +08:00
test_wave_attention_kernels.py
[AMD] Support Wave attention backend with AMD GPU optimizations (#8660)
2025-08-12 13:49:11 -07:00