Commit Graph

Select branches

Hide Pull Requests

dsv41-pd

dsv41-pd-visioncp

main

Mono Color

• e980c1a2f1 fix(glm4v): disambiguate mixed image video offsets (#37971) 3 people 2026-09-05 13:16:16 +08:00
• 0454c074b4 [mem_cache] Clean up unified allocator leftovers (#38103) Liangsheng Yin 2026-09-04 22:02:50 -07:00
• 3a770da756 [Unified Tree] Support Branching-Point Caching for the SWA Component (#34565) 3 people 2026-09-05 12:29:16 +08:00
• 991368d880 Fix Muse Glimmer ModelOpt mixed weight mapping (#37510) Po-Han Huang (NVIDIA) 2026-09-05 11:53:55 +08:00
• ecd97de1fc [Router] Add load-aware prefill admission and bounded policy proposals (#37843) 4 people 2026-09-05 11:53:26 +08:00
• d50e9a9756 [Test] Prune redundant unified-memory allocator and pool tests (#38093) Liangsheng Yin 2026-09-04 20:47:01 -07:00
• 92a4d8b5ee Clean logging under --weight-loader-prefetch-checkpoints (#33930) 3 people 2026-09-04 23:05:53 -04:00
• 0645398a32 [mem_cache] Move the unified-memory allocators into allocator/ and split the composites out (#38072) Liangsheng Yin 2026-09-04 19:53:15 -07:00
• d6e0a8cbf4 [diffusion] add Helios per-token gated-residual fusion (quality-gated) (#38042) Xiaoyu ZhangandBBuf 2026-09-05 10:29:09 +08:00
• f1f2380d2b [Unified Cache][6/N]: Add UMBP external linker (#37578) Niko MaandZhangheng 2026-09-05 09:21:43 +08:00
• bc727bc4ee [FP8] SM120: route FP8 linear to per-tensor (cudnn/nvjet) instead of channelwise cutlass (#38006) Xiaoyu ZhangandBBuf 2026-09-05 09:07:13 +08:00
• 55bf3380e0 Support Hy4-preview (#36805) 3 people 2026-09-05 09:03:49 +08:00
• 85da5457de [diffusion] auto-keep video DiT resident on high-memory GPUs (#38001) Xiaoyu Zhang 2026-09-05 08:54:09 +08:00
• 3c2724c48d [AMD] Optimize Kimi-K3 Triton MLA prefill on gfx950 (#35770) 5 people 2026-09-04 19:44:30 -05:00
• 3b64169f9d [Cookbook] Kimi-K3: add measured B300 1x8 Unified 8k/1k speed numbers (#37878) zijiexiaandClaude Opus 5 2026-09-04 17:44:00 -07:00
• a44bb397a9 [Perf] Vectorize alloc_extend_naive to remove the per-request Python loop (#37938) Alex Nails 2026-09-04 17:26:25 -07:00
• 613d87becd [Memory] Reuse output storage across full prefill CUDA graphs (#38038) Lianmin Zheng 2026-09-04 17:23:31 -07:00
• 65f7957142 fix: gather CP-sharded tokens before TP-sharded dense MLP under prefill CP (#38078) YAMY 2026-09-04 17:14:31 -07:00
• 8a98f11078 [feature] Add response-level input/output token ids to chat completions via SglExt (#34488) Amy Chang 2026-09-04 18:45:13 -05:00
• 9c254df8cd [diffusion] fix: preserve mapped courier tensor lifetime (#37965) PengYuanandMick Qian 2026-09-05 07:41:47 +08:00
• db89f639ef [GDN] Amortize ReplaySSM checkpoint materialization (#35544) YAMY 2026-09-04 15:13:20 -07:00
• e3eeabbbfa [Profiler] Add SGLANG_PROFILE_BY_STAGE_DECODE_MIN_BS to defer the decode-stage capture (#38067) Hanming Lu 2026-09-04 15:12:55 -07:00
• 0eff0f7460 Add num_prealloc_ready_tokens to decode load snapshot (#38065) cctry 2026-09-04 15:05:57 -07:00
• 320bdd1ee2 [Docs] Document --retraction-policy, --return-hidden-states-mode, --language-model-only (#37989) 4 people 2026-09-04 22:26:28 +01:00
• 3e873c2110 [Docs] Clarify OpenAI chat template defaults (#32172) alpandXinyuan Tong 2026-09-04 14:22:05 -07:00
• fbf8f1dbf6 [Fix] Coordinate FullCG prefix variants across DP ranks (#37888) Yongji WuandLianmin Zheng 2026-09-04 11:29:30 -07:00
• c8ba8996c4 Update DeepSeek-V4 Pro for B200 FP4 agentic HiCache DSpark (#38026) Faradawn Yang 2026-09-04 11:09:24 -07:00
• 010dc955be [Metrics] Export scheduler stage wall time (#37636) Jialin OuyangandPranjal Shankhdhar 2026-09-04 10:45:53 -07:00
• 07199fa220 [Performance] Optimize Qwen3.5 GDN prefill projection layouts (#36267) YAMY 2026-09-04 10:32:44 -07:00
• 55509b3f42 [NPU] Optimize the execution logic of NPU pr‑test tasks (#38015) 3 people 2026-09-05 00:19:50 +08:00
• 01e19ddf55 chore: add code owners for the Rust radix tree core (#38021) Shuwen WangandClaude Fable 5.1 2026-09-04 23:40:34 +08:00
• 5cd2a7661d fix: reformat cosmos3_edge.py to satisfy ruff-format (#38023) Shuwen WangandClaude Fable 5.1 2026-09-04 23:39:36 +08:00
• 0d0e2f92be [HiCache] Buffer mode support sidecar pool (#37424) huangtingweiandZhiqiang Xie 2026-09-04 23:24:18 +08:00
• 8b1d8c1703 [Metrics] Add rolling scheduler utilization counters (#37461) 3 people 2026-09-04 08:06:17 -07:00
• 4349538c02 [model] add cosmos3 reasoner to llm only inference (#33572) 5 people 2026-09-04 16:11:58 +02:00
• 19b46863f3 fix: align write-through pending across tree cores (#37278) Shuwen Wang 2026-09-04 22:08:25 +08:00
• 88021b0734 [diffusion] chore: make nightly performance measurements robust (#37915) Mick 2026-09-04 22:03:25 +08:00
• dc6b5d1f5a [CI][NPU] Remove model tests from PR-test pipeline (#38011) hhhh1252023 2026-09-04 21:26:52 +08:00
• 978cc228ca [Rust] Bound multimodal media ingress (#37967) Lianmin Zheng 2026-09-04 05:22:44 -07:00
• e4adf63275 [Fix] Vacuous marker writes in the cache tests, and an undebited Mamba admission slot (#36415) Shuwen WangandClaude Opus 5 2026-09-04 19:43:17 +08:00
• 3b678549c3 [diffusion] chore: warm up minimax-h3 at the served clip shape (#37945) Kevin MiandClaude Fable 5.1 2026-09-04 04:18:02 -07:00
• f3b2725609 sm120 32GB mem-tier: raise decode cuda-graph max_bs 24->48 + chunked_prefill 2k->4k (#37898) Xiaoyu Zhang 2026-09-04 18:47:26 +08:00
• 12735c2d76 [mm] refactor mm code for rust tokenizer manager (#34660) 4 people 2026-09-04 03:03:25 -07:00
• b42569a0f1 [Quant][ue8m0 fix] group requant_weight_ue8m0 reduce reserved gpu memory (#31755) CSWYF3634076androot 2026-09-04 18:03:21 +08:00
• d7f235daca [Memory] Retire graph borrow pool before updating static runs (#37966) Lianmin ZhengandShiyan Deng 2026-09-04 02:59:52 -07:00
• 2216697f90 [Docs] Refresh TPU model list and link cookbooks (#37750) Brian 2026-09-04 17:28:57 +08:00
• 44c786679f [sp] Make attention-TP sequence sharding a per-forward batch property (#37546) 3 people 2026-09-04 02:11:03 -07:00
• 67248e04b4 [mem_cache] Route hybrid SWA full-side kv-row frees through free_segment (#37876) 3 people 2026-09-04 01:48:33 -07:00
• dae126d510 [AMD][DSv4] Fuse inverse-RoPE into the fp8 wo_a quant (stacked on #37423) (#37658) karverma-amdandwunhuang 2026-09-04 02:51:29 -05:00
• 0b57847ebf Fix mamba radix cache ssm state indexing (#37836) Ke Baoandadityakamat24 2026-09-04 15:46:33 +08:00
• 01e66a62db [Diffusion] Improve BCG warmup frame-count diagnostics for video models (#37890) Xiaoyu Zhang 2026-09-04 15:05:24 +08:00
• 7f89cc5286 [AMD] Skip unused TOPK v2 plan kernel on ROCm (#37580) AMD-yanfeiwangandkk 2026-09-04 15:00:38 +08:00
• 1bda9694b7 [AMD][DSv4] Switch output projection gemm (oproj_a) to fp8 (#37423) 3 people 2026-09-04 12:26:07 +05:30
• b168f905c8 [Intel GPU] Align XPU toml file for rust support (#31031) Polisetty V R K Jyothendra Varma 2026-09-04 12:18:30 +05:30
• 31ebd8f437 [AMD][DSv4] Fuse the DSv4 FP4 indexer prefill-schedule preamble into one kernel (#37764) Hemanth Acharya 2026-09-04 12:14:49 +05:30
• 54c2c99feb [Diffusion] Fuse LingBot per-token gated residual and RMSNorm modulate (#37910) Xiaoyu Zhang 2026-09-04 14:35:13 +08:00
• cb32dbc9e0 [AMD] [Kimi-K3] Fuse the KDA input projection into a single GEMM on ROCm (#35176) Yu-Yun ChangandHAI 2026-09-04 14:30:08 +08:00
• 72078cd7f5 [XPU] Support GPT-OSS MXFP4 checkpoints on Intel XPU (#35751) 3 people 2026-09-03 23:20:28 -07:00
• d122ca99b2 [Bugfix] Fix Llama 4 FA3 local attention with paged KV cache (#32902) Po-Han Huang (NVIDIA)andkpham-sgl 2026-09-04 14:15:23 +08:00
• 4e756ecc4a [AMD] CI: fix Lean decode crash on the EAGLE path (#37119) mqhc2020andBingxu Chen 2026-09-04 14:04:21 +08:00
• 7825e5ffca [AMD] Fix DSV4 unified attention sink TP slice (#35092) AMD-yanfeiwangandkk 2026-09-04 13:59:53 +08:00
• ebae8ee21e [Fix] Register triton.runtime.cache.triton_key in the MPS stub so torch.compile keeps working (#37937) Alex NailsandClaude Opus 5 2026-09-03 22:56:14 -07:00
• 06b8749803 [Diffusion][Docs] Add single-GPU large-VRAM performance notes (B300) (#37891) Xiaoyu Zhang 2026-09-04 13:33:28 +08:00
• ed67b73081 [diffusion] UX: reduce hot-path server log noise (#37804) Mick 2026-09-04 13:31:00 +08:00
• 225129fe44 [AMD] Update v4 amd cookbook 0903 (#37829) Thomas Wang 2026-09-04 13:11:13 +08:00
• ca7b8efd87 [CI] Fix handle_platform_cp_compatibility reading legacy CP flags off the record (#37930) Mohammad Miadh AngkadandMohammad Angkad 2026-09-04 13:07:04 +08:00
• f478b2bb2d Fix: abort handling for dispatched requests after client disconnect (#35255) 3 people 2026-09-04 12:51:57 +08:00
• e787de5478 [XPU][CI] Move XPU tests to nightly and add per-subclass server launch timeout (#37532) ashwini rathi 2026-09-04 10:21:26 +05:30
• 3ad3f23ed5 [Comm] Drop the in-tree MNNVL CuTe DSL port in favor of FlashInfer 0.6.18 (#37206) Mohammad Miadh Angkad 2026-09-04 12:49:48 +08:00
• e3305b3b87 Add code owner for sglang-simulator (#37922) Zhangheng 2026-09-04 12:20:48 +08:00
• 97d081ac76 [diffusion] chore: remove unreachable cosmos3 transfer encoding (#37805) Mick 2026-09-04 12:14:03 +08:00
• ff1285cc28 [CP V1 Deprecation 2/5] Make strategy prefill CP canonical (#36223) Baizhou Zhang 2026-09-03 20:24:19 -07:00
• 59799a3687 [Simulator] Add high-fidelity CPU-based inference simulator (#33824) 4 people 2026-09-04 11:12:11 +08:00
• a5f07b1241 [CI] Build the Rust extensions for aarch64 too (#37820) Mohammad Miadh AngkadandMohammad Angkad 2026-09-04 10:54:08 +08:00
• 8770c1db1f [CPU][CI]: rename Xeon CPU CI suites to stage-*-intel (#37395) junduandMa Mingfei 2026-09-04 10:08:41 +08:00
• c1b4d535d7 [CI] Fix lint (#37895) Mohammad Miadh AngkadandMohammad Angkad 2026-09-04 09:37:50 +08:00
• 5e81d462c3 [diffusion] fix: only use fused qk_norm on nvidia gpu (#33994) Aleksi Vesanto 2026-09-04 04:25:08 +03:00
• 6c63d678d5 [diffusion] webui: fix minimax h3 webui inference settings (#36320) Li Jinliang 2026-09-04 09:24:14 +08:00
• 94eb15eb6c [diffusion] quant: support fp8 mixed precision for cosmos3 (#36380) Kedi WuandKedi Wu 2026-09-03 18:23:38 -07:00
• 667bc043dc [CI] remove MINIMAX_H3_HF_TOKEN (#37687) Yihao Wang 2026-09-03 18:22:32 -07:00
• 2a0602c7ac [diffusion] optimization: unfused w2 bias on SM12.x (cuBLAS 16x16 kernel mis-dispatch) for minimax-h3 vae decoder: (#37835) Mick 2026-09-04 09:17:23 +08:00
• 795dd7abce [diffusion] feat: compose third-party component bundles safely (#37816) Mick 2026-09-04 09:15:05 +08:00
• 516cfbd362 Fix UNO test adapter subdirectory resolution (#37872) eigenandYingyi Huang 2026-09-03 18:07:09 -07:00
• 9ed2721c6d [NPU] fix extend_seq_lens_cpu shape in eager mode (#36843) heziiop 2026-09-04 09:03:30 +08:00
• 6147a54ddf [PD] Bound transfer engine init with SGLANG_DISAGGREGATION_ENGINE_INIT_TIMEOUT (#37874) Liangsheng Yin 2026-09-03 17:16:55 -07:00
• 66d60433c1 state_capturer: pin the exact host-cache size via mmap + cudaHostRegister (#37285) Yueming Yuan 2026-09-03 16:20:59 -07:00
• 8b0501399e [CI] Improve Lark CI cards: structured layout, PDT timestamps, slow-only queue digest (#37884) Liangsheng Yin 2026-09-03 16:18:56 -07:00
• b44496389c [HiCache] Count hit allocations and in-flight backups in the buffer pipeline idle check (#37883) Zhiqiang Xie 2026-09-03 16:08:50 -07:00
• a480f388b2 [HiCache] L3 storage prefetch lifecycle metrics and cross-tier attribution fixes (#37503) Zhiqiang Xie 2026-09-03 16:00:04 -07:00
• 0610a6539d [CI] Add Lark notifications for CUDA CI status, runner health, and queue time (#37881) Liangsheng Yin 2026-09-03 15:46:33 -07:00
• 4dc9cda5f9 [PD] Gate deferred decode KV release on backend capability (#37454) Yonghao Zhuangandyhzhuang 2026-09-03 15:42:21 -07:00
• fd70325c10 [CI] Add dspark + dsv4 e2e test (#37665) Baizhou Zhang 2026-09-03 14:26:25 -07:00
• 4372b8efa7 [1/N] Quantization Refactor: remove dead code and dedup the FP4 marlin helpers (#37552) Mohammad Miadh Angkad 2026-09-04 05:22:31 +08:00
• 0e5414fd2f [Test] Allow top-k cutoff ties in test_sampling_mask_matches_topk_logprobs (#37873) Liangsheng Yin 2026-09-03 14:13:26 -07:00
• 05dbe64dff Fix buffer-mode idle tracking and VLM memory sizing (#37567) Lianmin Zheng 2026-09-03 13:56:12 -07:00
• 2a980cbf10 [mem_cache] Require page-aligned starts in free_segment and drop the boundary trim (#37729) Liangsheng Yin 2026-09-03 13:28:33 -07:00
• 3ffacf949b [Docs] [BugFix] Sync --tool-call-parser and --reasoning-parser lists with the code (#37788) Martin Hickey 2026-09-03 21:17:33 +01:00
• d0c95f6c91 [HiCache] buffer mode: anchor-lock staged prefetches by default (#37464) Zhiqiang Xie 2026-09-03 12:08:22 -07:00
• 68978f8d52 [Scheduler] Count the parked chunked-prefill request in the busy mem check (#37502) Zhiqiang Xie 2026-09-03 12:08:17 -07:00
• 2da5802bfa [Cookbook] DeepSeek-V4 DGX Spark: v2 image + Flash Official NVFP4 and Flash Vision FP4 cells (#37737) Jimmy ShongandClaude Fable 5.1 2026-09-03 11:43:01 -07:00