sglang

test_compressed_tensors_models.py

[CI] Share VLM engines and prune launch matrices on the per-commit H100/H200 suites (#33944 )

2026-08-07 01:22:22 -07:00

test_deepseek_v3_fp4.py

test/registered: cleanup pure model e2e tests (moves, splits, dedup, kit) (#26610 )

2026-05-28 15:41:46 -07:00

test_deepseek_v3_mtp.py

[Spec] Redo: split init_backends; account draft weights in --mem-fraction-static (#28855 )

2026-06-21 20:45:16 -07:00

test_deepseek_v4_flash_fp4_b200.py

[DeepSeek V4] Default FP4 checkpoints to FlashInfer MXFP4 MoE (#35919 )

2026-08-21 16:48:58 -07:00

test_deepseek_v4_flash_fp4_h200.py

Install DeepEP from release wheels (#33932 )

2026-08-07 15:38:44 -07:00

test_deepseek_v4_flash_fp4_megamoe_b200.py

[DeepSeek V4] Add W4A4 MegaMoE server flag (#35918 )

2026-08-21 18:44:18 -07:00

test_deepseek_v4_flash_fp8_h200.py

Clean deprecated DeepSeek V4 Environs (#34926 )

2026-08-17 16:07:00 -07:00

test_dsa_glm52_dp_mtp.py

Update GLM tests to 5.2 and delete redundant tests (#29686 )

2026-06-29 23:04:26 -07:00

test_dsa_glm52_hisparse.py

Update GLM tests to 5.2 and delete redundant tests (#29686 )

2026-06-29 23:04:26 -07:00

test_dsa_glm52_nvfp4_dp_mtp.py

[CI] Add GLM52 NVFP4 MTP B200 tests (#30021 )

2026-07-03 13:43:38 -07:00

test_dsa_glm52_nvfp4_tp_mtp.py

Bump FlashInfer to 0.6.15.post1 (#31927 )

2026-07-22 14:21:59 -07:00

test_dsa_glm52_pd_mtp_cp_layersplit.py

[CI] Re-enable B300 jobs (#35607 )

2026-08-22 12:34:21 +08:00

test_dsa_glm52_tp_mtp.py

Update GLM tests to 5.2 and delete redundant tests (#29686 )

2026-06-29 23:04:26 -07:00

test_dummy_grok_models.py

[Test] Stage-a sanity kits; consolidate core/ + models_e2e/ tests (#25831 )

2026-05-20 01:58:48 -07:00

test_gemma4_fp8_per_expert_loading.py

[Test] Stage-a sanity kits; consolidate core/ + models_e2e/ tests (#25831 )

2026-05-20 01:58:48 -07:00

test_generation_models.py

[CI] Share VLM engines and prune launch matrices on the per-commit H100/H200 suites (#33944 )

2026-08-07 01:22:22 -07:00

test_gpt_oss_4gpu_mxfp4.py

[misc] Use --cuda-graph-max-bs-decode in tests, examples, and docs (#29591 )

2026-06-28 18:38:28 -07:00

test_gpt_oss_sm120.py

[Test] Stage-a sanity kits; consolidate core/ + models_e2e/ tests (#25831 )

2026-05-20 01:58:48 -07:00

test_inkling_small_nvfp4.py

test: switch the Inkling-Small NVFP4 deterministic suite to DSPARK (#35293 )

2026-08-20 21:54:52 +08:00

test_inkling.py

Fix deterministic inference for Inkling (#33417 )

2026-08-08 07:48:15 +08:00

test_kimi_k3_b300.py

[CI] Re-enable B300 jobs (#35607 )

2026-08-22 12:34:21 +08:00

test_kimi_linear_models.py

Fix KDA prefix caching under mamba extra_buffer and enable it for kimi_linear (#31474 )

2026-07-19 20:09:03 +08:00

test_kimi_linear_unified_memory.py

[CI] Key scheduled CUDA suites by runner_config instead of hand-written jobs (#34186 )

2026-08-09 16:44:53 -07:00

test_mimo_v2_flash.py

[CI] Share VLM engines and prune launch matrices on the per-commit H100/H200 suites (#33944 )

2026-08-07 01:22:22 -07:00

test_mimo_v2.py

[HiCache]Asymmetric pool support direct backend (#28446 )

2026-06-16 13:17:57 -07:00

test_minimax_m25_basic.py

[CI] Share VLM engines and prune launch matrices on the per-commit H100/H200 suites (#33944 )

2026-08-07 01:22:22 -07:00

test_ministral3_models.py

[Test] Stage-a sanity kits; consolidate core/ + models_e2e/ tests (#25831 )

2026-05-20 01:58:48 -07:00

test_ministral4_models.py

[Test] Stage-a sanity kits; consolidate core/ + models_e2e/ tests (#25831 )

2026-05-20 01:58:48 -07:00

test_nvidia_nemotron_3_nano.py

[Bugfix] Fix Nemotron ForwardFlags across custom op boundary (#30968 )

2026-07-12 22:10:23 -07:00

test_nvidia_nemotron_3_super_bf16_mtp.py

test/registered: cleanup pure model e2e tests (moves, splits, dedup, kit) (#26610 )

2026-05-28 15:41:46 -07:00

test_nvidia_nemotron_3_super_bf16.py

test/registered: cleanup pure model e2e tests (moves, splits, dedup, kit) (#26610 )

2026-05-28 15:41:46 -07:00

test_qwen3_next_models_extra.py

[CI] Trim the base-c 4-gpu-h100 stage from 5 shards to 4 (#35407 )

2026-08-19 00:48:07 -07:00

test_qwen3_next_models_mtp.py

[CI] Share VLM engines and prune launch matrices on the per-commit H100/H200 suites (#33944 )

2026-08-07 01:22:22 -07:00

test_qwen3_next_models.py

[CI] Trim the base-c 4-gpu-h100 stage from 5 shards to 4 (#35407 )

2026-08-19 00:48:07 -07:00

test_qwen35_fp4_mtp.py

[ModelOpt FP4] Support online MoE weight quantization (#33115 )

2026-08-06 11:01:55 -07:00

test_step3p5_flash_chain_mtp.py

[CI] Collapse the EAGLE launch matrix and the scoring engine boots on the per-commit runners (#33756 )

2026-08-05 16:43:19 -07:00

test_transformers_backend_eval.py

[CI] Share VLM engines and prune launch matrices on the per-commit H100/H200 suites (#33944 )

2026-08-07 01:22:22 -07:00

test_transformers_models.py

[CI] Route mmlu and GB300 MMMU-Pro evals through sgl-eval (#34477 )

2026-08-12 19:33:21 -07:00

test_vlm_models.py

[CI] Share VLM engines and prune launch matrices on the per-commit H100/H200 suites (#33944 )

2026-08-07 01:22:22 -07:00