Commit Graph
18707 Commits
Author SHA1 Message Date
Leon GaoandAndrew Gu ee678910f7 [Kernel] Skip KV writes to reserved padding slots (#32477)
Co-authored-by: Andrew Gu <andrew@thinkingmachines.ai>
2026-07-29 09:58:18 +08:00
gjsheu d86492fea0 [NPU] adapt dflash v2 on npu (#31739) 2026-07-29 09:39:19 +08:00
amote-i cb12a1547b [NPU] [DOC] update supported features on ascend npu (#32647) 2026-07-29 09:05:21 +08:00
Lianmin Zheng 16a52bff23 [Refactor] Move sampling tokenizer validation helper (#32694) 2026-07-28 16:48:03 -07:00
YAMYandLee Nau 86ee545388 docs(cookbook): update Kimi-K3 GB200 recipes from measured 4x4 runs (#32592)
Co-authored-by: Lee Nau <lnau@nvidia.com>
2026-07-28 16:26:40 -07:00
Lianmin Zheng 9ca4023b13 [Core] Clean up array-like msgspec structs (#32688) 2026-07-28 16:25:22 -07:00
Mick 70ea37e7e0 vlm: reject moss vision metadata mismatches (#31957) 2026-07-29 07:09:54 +08:00
Xiaoyu Zhang c9947b087b Enable multimodal prefill BCG for VL and audio models (#30872) 2026-07-29 06:47:40 +08:00
Liangsheng Yin 85618cc798 docs: update sglang cookbook (#32654) 2026-07-28 15:33:24 -07:00
Xiaoyu Zhang 7778dd23ea [diffusion] refactor: remove stale kernels and dead code (#32651) 2026-07-29 06:23:23 +08:00
Void 7f438a6031 feat: SM120 (Blackwell Desktop) support for GLM-5.1 inference (#26928) 2026-07-28 14:52:34 -07:00
Qiaolin YuandZijie Xia 9c0dbf508f [cookbook] add inkling dspark command (#32465)
Co-authored-by: Zijie Xia <zijie.xia@radixark.ai>
2026-07-28 14:33:38 -07:00
Ethan (Yusheng) Su 0a49226d19 [LoRA] 1/n Per-rank tensor serialization for load_lora_adapter_from_tensors under dp_size > 1 (#32580) 2026-07-28 14:28:56 -07:00
Rain Jiang d943636a48 support regex that compatible with python re lib however apply more l… (#32676) 2026-07-28 14:25:31 -07:00
YAMY dd67452b4f [Cleanup] Move mamba-max-states-per-path validation into _handle_mamba_backend (#32502) 2026-07-28 14:21:21 -07:00
Qiaolin Yu b8b9f3c8f5 [misc] update CI_PERMISSIONS.json (#32679) 2026-07-28 14:12:29 -07:00
paulzhang-tmandClaude Fable 5 4e5a05148a [FullCG] Support chunked cached-prefix prefill (#30825)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 11:20:25 -07:00
IvanShan177andClaude Opus 4.8 1eee8fbdcc [PD] Drain NIXL completion notifications before enforcing the WaitingForInput timeout (#32267)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-29 00:20:03 +08:00
Xinyuan TongandFAN YUCHEN ee236086db Fix invalid escape warnings in tool parsers (#28370)
Co-authored-by: FAN YUCHEN <2994114386@qq.com>
2026-07-28 23:31:47 +08:00
Mick 84cdfde5b2 [diffusion] fix: fix diffusion output stability on mps (#30017) 2026-07-28 21:55:03 +08:00
32c30c0f96 Return 400 instead of 500 for unfetchable or unparseable multimodal inputs (#31417)
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
2026-07-28 05:23:42 -07:00
Mick 161fffedfc docs: clarify diffusion stage reuse guidance (#32639) 2026-07-28 19:52:52 +08:00
Mick 75017c3fa0 [diffusion] fix: keep fused qk-norm-rope out of dynamo tracing (#31849) 2026-07-28 19:51:00 +08:00
Mick a24906a091 [diffusion] feat: add dynamic cuDNN SDPA attention backend (#30090) 2026-07-28 19:50:24 +08:00
Talantan1102 5558dbad00 [NPU] Optimize DeepSeek-V4 performance (#31931) 2026-07-28 19:45:46 +08:00
James LiuandClaude Opus 4.8 51397af885 Pack aux hidden states into a preallocated buffer (#28956)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-28 04:37:18 -07:00
4fe8f5218d [AMD] Add Kimi K3 ROCm 7.2 nightly image (#32643)
Co-authored-by: bingxche <bingxche@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-28 18:45:23 +08:00
Xiaoyu Zhang 9cffc2ba52 [Kernel] Remove unused implementations and stale registry entries (#32636) 2026-07-28 18:12:10 +08:00
hjzhangandhjzhang dde03d7c4a [JIT] Restore the previous division behavior in per-token group quantization (#32616)
Co-authored-by: hjzhang <zhanghjzzz@qq.com>
2026-07-28 17:56:36 +08:00
YC Yen-Ching Tsengandbingxche 2b6e01c673 [AMD] Run AITER Scout on Saturdays (#32632)
Co-authored-by: bingxche <bingxche@amd.com>
2026-07-28 16:56:51 +08:00
Zhangheng 60d6914f17 [UnifiedTree]: move /mem_cache/unifed_cache_component dir to /mem_cache/unified_cache (#32484) 2026-07-28 16:28:21 +08:00
Xinyuan Tongandliyucheng09 fc8b328f5c [Model] Support standalone text-only Qwen3.5 checkpoints (#32401)
Co-authored-by: liyucheng09 <liyucheng09@gmail.com>
2026-07-28 14:08:39 +08:00
Alex Nails ec4a7fa2b7 codeowners update (#32608) 2026-07-27 21:21:20 -07:00
Yuan Luoandluoyuan.luo d9cf7b0a8b [MTP] Cut spec-v2 host-seam overhead in hybrid-linear MTP decode (#32219)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
2026-07-28 11:38:33 +08:00
zijiexiaandClaude Opus 5 b79388f338 docs(cookbook): mark every Kimi-K3 cell in-progress; land Playground "Switch base" on the configurator (#32586)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-07-27 18:59:57 -07:00
longxin9715 356c11d5d9 [Fix] --mm-process-config crash when video config contains (#30260) 2026-07-28 09:24:40 +08:00
sglang-botandsglang-bot edc0e5489f docs: sync LMSYS SGLang blog cards (#32590)
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
2026-07-27 18:00:29 -07:00
Lianmin Zhengandcctry c19a333944 [mm] Handle per-item embeddings in cache misses (#32498)
Co-authored-by: cctry <cctry@meta.com>
2026-07-27 17:16:17 -07:00
Caio RochaandCheng Wan 5a46e16f01 [Fix] Enable graph capture and MSCCL++ for attention TP groups (#31629)
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
2026-07-27 15:56:41 -07:00
Mohammad Miadh Angkad 3005af0941 Fix compressed-tensors NVFP4 MoE W13 layout (#32430) 2026-07-27 14:56:42 -07:00
Kangrui Du 8a311d1c88 [diffusion] fix: preserve tensor stride when offloading rollout weights to pinned host memory (#32420) 2026-07-27 12:05:13 -07:00
James Liu 1da062f018 [Inkling] Add minimal DFLASH support (#31840) 2026-07-27 12:01:13 -07:00
Yuhao Yang 7cae831e41 Update mi35x ROCm image to k3-20260727 (#32559) 2026-07-27 10:52:41 -07:00
Mohammad Miadh AngkadandXinyuan Tong 3ebb7c2d07 docs: point Kimi-K3 references to public branch (#32547)
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2026-07-27 16:23:43 +00:00
7dafacca49 docs(cookbook): add the Kimi-K3 serving cookbook (#32542)
Co-authored-by: kpham-sgl <khoa.pham@radixark.ai>
Co-authored-by: Zijie Xia <zijie.xia@radixark.ai>
Co-authored-by: ispobock <ispobaoke@gmail.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: thomawan <thomawan@amd.com>
Co-authored-by: BBuf <1182563586@qq.com>
2026-07-27 08:37:30 -07:00
8d6549bc40 [Attention Backend] Extend hpc_ops dynamic-scheduled decode to bf16 (#32304)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Halcyon <56064364+VAthree@users.noreply.github.com>
2026-07-27 21:31:04 +08:00
inkcherry 5656de2d9a [PD] pool decode bootstrap HTTP sessions (#31543) 2026-07-27 21:07:23 +08:00
Peng Xingchen db9143ee08 [NPU] Fix MTP IndexShare warm-up for attention DP and prefill CP (#32210) 2026-07-27 19:19:38 +08:00
Lianmin Zheng 34454c06b8 [Refactor] Tidy server_args.py section grouping and drop unused alias (#32496) 2026-07-27 04:09:09 -07:00
1d350aaad3 fix(reasoning): let --enable-strict-thinking works for DeepSeek-V4 (#32400)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2026-07-27 18:15:47 +08:00