Commit Graph

Select branches

Hide Pull Requests

bot/update-est-time-20260928

dsv41-pd

dsv41-pd-visioncp

main

Mono Color

• 35a4c21a8a update CI permission list (#13962) Zaili Wang 2025-11-26 12:16:44 +08:00
• 846ba3c62c Fix nightly test failures: NSA indexer dtype and CPP radix cache init (#13958) alisonshao 2025-11-25 19:52:08 -08:00
• 18fb51583f Support FlashAttention3 page_size > 1 and topk > 1 case with paged attn and spec decode (#7725) Yubo Wang 2025-11-25 19:44:41 -08:00
• ca5c8b16f6 [VLM] Support InternVL Vision Encoder Data Parallelism (#13925) Yuan Luoandluoyuan.luo 2025-11-26 11:43:05 +08:00
• f33e5d1ef1 fix: spec overlap predict shape does not match verify output shapes (#12786) timmy-feng 2025-11-25 19:01:06 -08:00
• 13e5beeab4 Fix Deepseek v3.1 loading issue (#13954) Kangyan-Zhou 2025-11-25 18:28:52 -08:00
• c53e729d45 chore: bump sgl-kernel version to 0.3.18.post1 (#13951) sglang-botandsglang-bot 2025-11-25 18:14:28 -08:00
• 03a26557b7 Fix nightly-test-nvidia.yml to have the correct trigger (#13950) Kangyan-Zhou 2025-11-25 17:34:34 -08:00
• 873382a910 [Tiny]Upgrade README for sgl-kernel (#13945) Baizhou Zhang 2025-11-25 16:46:30 -08:00
• 391a863b3f chore: bump sgl-kernel version to 0.3.18.post1 (#13942) sglang-botandsglang-bot 2025-11-25 15:31:53 -08:00
• 36b1bcd242 [chore] update torch version to 2.9 (#12969) Fan YinandBaizhou Zhang 2025-11-26 06:47:34 +08:00
• 64a11303ce Fix update weight error for blackwell DeepGEMM (#13910) fzyzcjy 2025-11-26 05:28:12 +08:00
• 1ab6ce0e62 [Auto Sync] Improve profilers and simplify bench_one_batch_server.py (#13866) Lianmin Zheng 2025-11-25 12:13:31 -08:00
• e99ca6ac74 Improve nightly tests (#13903) Kangyan-Zhou 2025-11-25 12:04:49 -08:00
• fcccaf9001 Add Llama4 attention backend auto-selection (#13421) Jan Bernlöhr 2025-11-25 20:54:21 +01:00
• 215a97fa6c Fix docstrings for v1 HiCacheStorage methods (#13851) Tova Movshovitz 2025-11-25 21:48:26 +02:00
• 5eed5fc0b0 [DeepSeekV3.2] Centralize NSA dispatch logic in NativeSparseAttnBackend (#13544) YAMYandhlu1 2025-11-25 11:32:30 -08:00
• 808b6dfdea [Minor] Fix lint (#13938) Baizhou Zhang 2025-11-25 10:57:23 -08:00
• 4852aa054c [misc] add llama3.1 chat template (#13935) Simo Lin 2025-11-25 09:31:54 -08:00
• f922bfd520 [CPU] Apply PR gating rule in CI workflow (#13933) Zaili Wang 2025-11-26 00:44:16 +08:00
• dfd7ab9682 [diffusion] feat: support LoRA (#13859) Mick 2025-11-26 00:21:33 +08:00
• 46673b4224 [diffusion] doc: add doc for LoRA usage (#13931) Mick 2025-11-26 00:02:14 +08:00
• 3421d049aa [CI] rename: per_commit -> registered (#13928) Liangsheng Yin 2025-11-25 23:05:06 +08:00
• d3d404d3d7 [CI] CI registry update (#13927) Liangsheng Yinandalisonshao 2025-11-25 22:43:19 +08:00
• 64225a8ae9 fix nixl prefill crash make decode health check failed (#13657) luchangli 2025-11-25 21:40:11 +08:00
• d64bf6c6ce Support piecewise cuda graph for Qwen3-next (#13081) Chen1022 2025-11-25 21:01:27 +08:00
• 432ecf841e [Ascend] qwen optimization (#12078) LiwansiandEven Zhou 2025-11-25 19:44:24 +08:00
• 0b3f002daf Update release-whl-kernel.yml (#13921) Ke Bao 2025-11-25 19:05:38 +08:00
• 6f094deff0 [diffusion] CI: minor refactor CI for less code duplication (#13905) Mick 2025-11-25 18:44:11 +08:00
• 59464dbf15 [Fix]: Further fix the buffer len of future map (#13916) ant-yy 2025-11-25 18:09:28 +08:00
• 1f7fcc10d5 [diffusion] profile: fix profiling bugs (#13642) Yi ZhangandMick 2025-11-25 17:58:35 +08:00
• dbab5d50a3 Add test_dummy_grok_models.py to not_in_ci section (#13908) alisonshao 2025-11-25 00:51:25 -08:00
• 760c20b360 update flashinfer_cubin==0.5.3 (#13848) Lzhang-hub 2025-11-25 16:10:34 +08:00
• 407cb3ce1e [CI tiny fix] Enhance robustness of vision chunked prefill test with ROUGE-L metric (#13793) Xiaoyu Zhangandgithub-actions[bot] 2025-11-25 15:41:14 +08:00
• 7cc43bd453 Move test_dummy_grok_models.py from manual to srt (temporary) (#13901) alisonshao 2025-11-24 23:36:53 -08:00
• cce2d748ef remove RoPE CPU fp32 tests (#13827) Zaili WangandFan Yin 2025-11-25 15:22:35 +08:00
• c1dd9a9599 [Fix] JIT kernel dependencies in other platforms (#13889) DarkSharpness 2025-11-25 15:19:17 +08:00
• ed8786b0b9 Adding nightly tests for Kimi-K2-thinking, Qwen3, minimax-m2, GLM4.6 (#13890) Douglas Yang 2025-11-24 22:47:46 -08:00
• f9fe06309f Fix trace publish paths in nightly-test-nvidia workflow (#13888) alisonshao 2025-11-24 21:58:26 -08:00
• 8ff3ef1fef fix: draft model revision misuse model revision (#11893) gongwei-130 2025-11-24 21:13:37 -08:00
• da182e4b83 [CI] fix lint error (#13891) Yibo Cai 2025-11-25 12:51:33 +08:00
• 83e7207763 [diffusion] CI: add validation and cleanup for corrupted safetensors in multimodal loader (#13870) 3 people 2025-11-24 20:02:43 -08:00
• a2c388ba11 [CI] fix multimodel-gen-test job (#13874) Yibo Cai 2025-11-25 11:46:23 +08:00
• 9384fa2729 [diffusion] refactor: remove training-related code (#13860) Mick 2025-11-25 11:38:50 +08:00
• 173e73fa1e Fix nightly test job to fail when any test fails (#13871) alisonshao 2025-11-24 19:33:46 -08:00
• a164259efd [Router bugfix] Fix router_manager selecting the wrong router when enable-igw. (#13572) Siyuan Chen 2025-11-25 10:51:41 +08:00
• b0a26ba624 Add support for bf16 x bf16 cutlass fused MoE (#10275) 3 people 2025-11-24 20:49:39 -06:00
• de430b6745 [Performance] Replace preprocess_video logic from GLM multimodal processor with transformer impl for speed up (up to 27% faster) and addressing OOM (up to 50x improvements) (#13487) Binyao Jiang 2025-11-24 18:17:13 -08:00
• 4b45d556a7 Overlap glm moe gemms in two cuda streams (#13786) Qiaolin Yu 2025-11-24 18:15:24 -08:00
• db0ffc09ef [NPU] Fix NPU CI (#13834) Even Zhouandc30031083 2025-11-25 10:09:36 +08:00
• eb1d885400 add LoRA warning if loading a preexisting LoRA adapter with a different name (#13822) Glen Liu 2025-11-24 18:16:41 -05:00
• bf10869203 [Doc] Add an Introduction to Expert Parallelism (#13783) Cheng Wan 2025-11-24 14:46:51 -08:00
• e83bd1fadc [Auto Sync] Update schedule_batch.py, schedule_policy.py, b... (20251122) (#13763) 4 people 2025-11-24 14:33:31 -08:00
• 9dc15d8569 fix xgrammar_backend crash with malformed inputs (#13752) gongwei-130 2025-11-24 13:54:19 -08:00
• fafaa2ccea [BugFix] fix outplace_fused_experts missing is_gated (#13864) Minglei Zhu 2025-11-24 12:36:14 -08:00
• 9b4b344115 [model-gateway] add grpc server code owner (#13865) Simo Lin 2025-11-24 12:29:57 -08:00
• 94216a9cc4 Fix quantized moe checker fail for Qwen3 dense fp8 model (#13853) fzyzcjy 2025-11-25 03:16:50 +08:00
• 9535015d05 [Perf] Optimize DeepSeek-R1 w4afp8 glue kernels (#10027) Yuhao YaoandFan Yin 2025-11-25 03:05:38 +08:00
• a3b578fc60 [model-gateway] Refactor router e2e responses tests (#13745) 3 people 2025-11-24 10:58:53 -08:00
• b60e769d0e Tiny unpin uvloop for other backends (#13858) Liangsheng Yin 2025-11-25 01:34:57 +08:00
• a95a38078b [Fix] Fix uvloop get_event_loop() is not suitable for 0.22.x (#13612) Zhi Yiliuandlzy 2025-11-25 01:20:00 +08:00
• 98b38de3f2 Fix: Safe RoPE Cache Expansion to Prevent Position-ID Out-of-Bounds in EAGLE + Long-Sequence Workloads (#11871) YAMY 2025-11-24 09:19:06 -08:00
• a146f833f1 [Fix]: Adjust FutureMap's token_id_bufs Size to Prevent ChunkedPrefill's next_token_ids from Overwriting Previous Prefill Requests' next_token_id (#13713) ant-yy 2025-11-25 01:08:52 +08:00
• 1dd9a6ae4d Fix TorchAO quant in VLM (#13508) StonyPortandqiuxuan.lzw 2025-11-24 22:15:40 +08:00
• 8ef11569a2 [VLM] Revise InternVL Piecewise CUDA Graph Supporting (#13846) Yuan Luoandluoyuan.luo 2025-11-24 22:15:10 +08:00
• ecefc7904f [sgl-kernel Code Clean] Remove useless lightning_attention kernel (#13819) Xiaoyu Zhang 2025-11-24 18:26:25 +08:00
• aeac622058 [Intel XPU]support xgrammar backend for intel xpu (#13245) gaopengff 2025-11-24 16:48:00 +08:00
• 04b52fa8d6 [chore]Upgrade flashinfer to 0.5.3 (#13751) Baizhou Zhang 2025-11-23 23:38:36 -08:00
• e5c0f59133 [diffusion] CI: send nightly-test outputs of diffusion to slack for correctness monitoring (#13833) Yuhao YangandMick 2025-11-24 15:22:26 +08:00
• 981ca8313f [misc] Rename minilb install env & remove files & fix lint (#13831) Liangsheng Yin 2025-11-24 13:50:00 +08:00
• 414248e0d0 [diffusion] doc: minor update contributing.md with test section (#13792) Mickandgemini-code-assist[bot] 2025-11-24 13:00:08 +08:00
• f56b9b42e6 [Bugfix] Add jit kernel files in packaging (#13829) 3 people 2025-11-24 12:32:16 +08:00
• b2f7b08c49 Refactor cache init logic (#13800) Liangsheng Yin 2025-11-24 11:41:46 +08:00
• 75222bfed9 Update MindSpore documentation (#13656) 3 people 2025-11-24 11:20:51 +08:00
• 9ea1953331 [Doc] Refine fused_moe_triton configs doc (#13820) Xiaoyu Zhang 2025-11-24 11:09:41 +08:00
• dbf22152d6 Fix bug: Incorrect variable used in rem_total_token_offset calculatio… (#13201) liuhuijiayou 2025-11-24 11:04:34 +08:00
• d5e0346847 xgrammar up version to 0.1.27 (#13650) Swipe4057 2025-11-24 05:53:45 +03:00
• a22104a676 chore: bump sgl-kernel version to 0.3.18 (#13816) sglang-bot 2025-11-23 17:24:54 -08:00
• 4683e244fe [1/2] Refactor DeepGeem requant for FP8 Linear on Blackwell (#13601) Baizhou Zhangandfy1214 2025-11-23 16:07:56 -08:00
• 9054e844ea remove package json which is not used (#13810) Simo Lin 2025-11-23 15:00:30 -08:00
• 18403f6bfe make trtllm attn backend's init_forward_metadat non blocking (#13802) yinghui 2025-11-23 22:35:40 +01:00
• 2892265d4c Tune fp8_w8a8 fused triton moe for GLM-4.6-FP8 (#13815) Qiaolin Yu 2025-11-23 13:29:54 -08:00
• c9bd1aca32 [CI] Tiny refactoring sgl-kernel tests (#13813) Baizhou Zhang 2025-11-23 12:45:17 -08:00
• 618ca23802 [Deepseek] Refactor deepseek server_args _handle_model_specific_adjustments (#13687) hlu1 2025-11-23 12:41:14 -08:00
• 5c2915494c [Scheduler] Tiny organize code style (#13806) Liangsheng Yin 2025-11-23 23:41:34 +08:00
• aaa40a9b3b Fix pagination bug in CI monitor preventing performance-test-2-gpu data collection (#13781) alisonshao 2025-11-23 06:02:30 -08:00
• dd70cf99c1 [diffusion] CI: add run_suite to multimodal_gen CI (#13791) Mick 2025-11-23 21:27:33 +08:00
• d4593964fe [diffusion] feat: support sp for image models (#13180) Mick 2025-11-23 18:11:42 +08:00
• 53fffefd5d Upgrade flashmla kernel for NSA tp support (#13718) YAMY 2025-11-23 01:36:49 -08:00
• b964ce61d6 [DeepEP] Add SGLANG_DEEPEP_BF16_DISPATCH env var in Normal mode (#13787) Xiaoyu Zhang 2025-11-23 17:32:43 +08:00
• ac5505b04c [Feature] HiCache JIT kernel (once again) (#13764) DarkSharpness 2025-11-23 14:19:16 +08:00
• a90435c059 Fix typo in docs (#13709) Peiqi Yin 2025-11-23 10:49:49 +08:00
• 5354d7b7fd [model-gateway] clean up router manager function order (#13776) Simo Lin 2025-11-22 16:16:20 -08:00
• e01486778a [model-gateway] update smg code owner (#13777) Simo Lin 2025-11-22 15:50:53 -08:00
• 047935080d Revert "Fix RMSNorm API CALL mismatch issue. (#10032)" (#13727) ErsongWang 2025-11-23 06:25:52 +08:00
• cad7878964 Gather static input buffers for cuda graph (#13676) cctry 2025-11-22 13:01:50 -08:00
• b29769f3b6 Move unnecessary input_addr capture under debug mode flag for speed-up (#13690) Binyao Jiang 2025-11-22 11:42:26 -08:00
• 3990b84bd3 Refactor MHA & MLA KV caches to support FP4 (#13547) Ho-Ren (Jack) Chuang 2025-11-22 11:13:43 -08:00
• 5a4394a342 align code style eagle draft&draft_extend cuda graph runner (#13533) yinghui 2025-11-22 18:55:16 +01:00
• dd303614e0 [diffusion] CI: tinyfix diffusion ci (#13769) Yuhao YangandMick 2025-11-23 01:03:36 +08:00