Commit Graph

Select branches

Hide Pull Requests

dsv41-pd

dsv41-pd-visioncp

main

Mono Color

• abed680320 [Unified Cache][5/N]: Integrate external linker mode end to end (#37381) Zhanghengand晟海 2026-09-04 02:02:58 +08:00
• 619ab2bcce Fix block-scale swizzling device placement (#37849) Lianmin Zheng 2026-09-03 10:47:04 -07:00
• 23ab10a63e Support speculative decoding with unified SWA memory (#36403) 3 people 2026-09-03 10:44:57 -07:00
• 33a22b1b08 [Cache] Forward fast prefix matching capability (#37844) cctry 2026-09-03 10:33:30 -07:00
• 54cadad151 [Router] Add composable scoring and eligibility policies (#37731) Vincent Gaoandinkcherry 2026-09-04 00:01:41 +08:00
• 392841f47c [Bugfix] Support K2 Horizon MoE without MoVA (#37825) Yash AkhauriandBBuf 2026-09-03 08:53:16 -07:00
• bf71035d39 [diffusion] MiniMax-H3: tiered AdaLN plan cache (pinned-host tier + per-plan LRU) (#37266) triple-muandmickqian 2026-09-03 22:09:21 +08:00
• 4e37882a93 [Diffusion][minimax-h3] Add SM120 support for SubBlock sparse attention (#37332) Quanli Liand全力 2026-09-03 22:05:22 +08:00
• 3239baef25 [CI][NPU] Fix kimi_k2_6 16p in64k perf test and dsv4-flash testcases (#37760) pllimax 2026-09-03 21:57:14 +08:00
• 9cb38a3d57 [diffusion] feat: filter duplicate precision variants across custom loaders (#37616) dujifengandmickqian 2026-09-03 21:54:11 +08:00
• f5bed255c0 [diffusion] feat: support key masks on USPAttention's replicated-prefix path (#36735) Yihao WangandClaude Fable 5 2026-09-03 05:13:33 -07:00
• 14444c6a04 [diffusion] feat: add maybe_record_function profiler spans for request phases (#35922) Yihao WangandClaude Fable 5 2026-09-03 05:12:54 -07:00
• 2bb25dc18b [Speculative Decoding] Add native UNO serving support (#37667) 3 people 2026-09-03 05:08:41 -07:00
• 354ed6d66b [NPU] [DOC] Refresh supported models and features on NPU (#37799) amote-i 2026-09-03 19:53:39 +08:00
• dd091f43cd [AMD] Update kimi-k3 amd cookbook 0903 (#37781) kkandwunhuang 2026-09-03 18:44:39 +08:00
• a11dba1a01 [Feature] Unified memory: support decode context parallelism for the trtllm_mla family (#37693) Cheng Wan 2026-09-03 03:37:12 -07:00
• f59a4840c5 [AMD][CI] Correct MI355X Slurm exclude node (#37779) YC Yen-Ching TsengandChen 2026-09-03 12:32:44 +02:00
• 429ac2d82c [AMD] Fix DSv4 draft extend taking the target compression path during prefill (#37713) Duyi-Wang 2026-09-03 17:46:49 +08:00
• 27b7a2dc3b [Kimi K3] Rework skipped-think fix as opt-in force_nonempty_content with streaming coverage (#34187) 3 people 2026-09-03 17:37:28 +08:00
• a6001478f4 [AMD] Perf Kimi-K3 MoE optimization (#33838) kkandwunhuang 2026-09-03 17:28:28 +08:00
• 397aeca376 fix(benchmark): support Glm4MoeLite in fused MoE tuner (#37623) Xiaoyu Zhang 2026-09-03 17:21:42 +08:00
• 7ed29eba80 [AMD] Fix FP4 indexer OOR (#37660) Xinyi SongandThomas Wang 2026-09-03 01:49:46 -07:00
• e59a576f03 fix test/manual/test_forward_split_prefill.py UT due to many refactors and design changes (#36617) Polisetty V R K Jyothendra Varma 2026-09-03 14:18:55 +05:30
• 3bac084d4e [Model] Add native IFM K2 Horizon serving support (#37654) 3 people 2026-09-03 01:39:43 -07:00
• 02d9b3060a [Docs] Update K2 Horizon MoE model names (#37723) Yash Akhauri 2026-09-02 23:32:44 -07:00
• 1fb85053e7 [AMD][Diffusion] Migrate FlyDSL fused norm kernels to the v0.3.0 stable API (#36349) YC Yen-Ching TsengandPhil Li 2026-09-03 08:03:08 +02:00
• 030d7e7e9b [ROCm] Define the DSA head-gate graph helpers on HIP (#37118) xiaobochen-amdandZhang, Jiejing 2026-09-03 13:55:45 +08:00
• 4b0edb25f2 [CPU] Update base image to Ubuntu 26.04 (#35313) Zaili Wang 2026-09-03 12:42:14 +08:00
• 54da74e83e [Fix] Broadcast PP dynamic-chunk profiling failures so every rank disables together (#37675) Liangsheng Yin 2026-09-02 21:09:04 -07:00
• 98ef7d8ae6 docs: add K2 Horizon cookbook recipes and H200 results (#37655) Yash Akhauri 2026-09-02 20:52:05 -07:00
• 49e6e81830 [CI] Accept t64-suffixed apt packages in the install skip check (#37689) Liangsheng Yin 2026-09-02 20:51:47 -07:00
• 81b0e4985a Modify KUBE_JOB_NAME to fix the problem of the string being too long (#37572) hhhh1252023 2026-09-03 11:43:36 +08:00
• cf3173aeb9 [Perf] Walk the radix tree by offset instead of re-slicing token storage (ported from #36507) (#37324) Khoa PhamandClaude Opus 5 2026-09-02 20:13:03 -07:00
• 57c26a84e0 [chore] Add .git-blame-ignore-revs for the black -> ruff-format reformat (#37210) (#37695) Alex NailsandClaude Opus 5 2026-09-02 20:01:48 -07:00
• 4229088a48 feat(kernels): generalize persistent CuTe JIT cache (#33911) James Liu 2026-09-02 19:59:04 -07:00
• 28262c20df [CI][RFC] Replace black-jupyter with ruff-format (#37210) Alex NailsandAlison Shao 2026-09-02 19:46:08 -07:00
• 2641e427be Xpu/weekly simple model enablement 2026 08 30 (#37193) 6 people 2026-09-02 18:35:59 -07:00
• a522c8a4b6 [misc] Extract PP dynamic chunk sizing into a DynamicChunkSizer scheduler component (#37674) Liangsheng Yin 2026-09-02 18:35:43 -07:00
• 0dd66def7c [chore] harden checkpoint quantization metadata parsing (#36922) Mick 2026-09-03 09:27:22 +08:00
• fbf909b460 [Fix] Alpha-channel images and tool-result media ordering (port of #36507) (#37320) 4 people 2026-09-02 18:23:06 -07:00
• 6e41f1ad29 [Fix] Preserve FP32 in SM107 MXFP8 fallback (#37489) Lee NauandYangmin Li 2026-09-02 20:55:14 -04:00
• 80e8302d03 Add SGLANG_CRASH_ON_JIT_COMPILE to forbid on-the-fly JIT compilation (#36615) Shiyan DengandLianmin Zheng 2026-09-02 17:26:25 -07:00
• 87d60a2229 Improve CUDA graph and speculative execution output handling (#37329) 5 people 2026-09-02 17:25:27 -07:00
• db1eb48651 [CI] Graceful teardown for the PD and HiSparse server fixtures (#37485) Alison Shao 2026-09-02 17:22:18 -07:00
• ff04a00d73 Reduce tokenizer overhead and offload CUDA VMM publication (#37330) 3 people 2026-09-02 17:21:08 -07:00
• f15748d965 [bench] Support real-traffic replay with early-stop-aware steady-state metrics in bench_one_batch_server (#37469) Oguz Ulgen 2026-09-02 17:20:25 -07:00
• 5c46ce37f5 [Fix] Apply the attention-CP broadcast result in PP dynamic-chunk profiling (#37669) Liangsheng Yin 2026-09-02 17:20:07 -07:00
• 3421d4375b [Docs] GLM-5.3-Flash cookbook: drop stale EP caveat, add B300/H100/B200 FP8 speed data (#37576) Xinyuan Tong 2026-09-03 08:16:23 +08:00
• 046cdaabaa [Sampling] Capture masks from sampler support (#36630) Byron HsuandByronHsu 2026-09-02 17:13:28 -07:00
• 5ddca6819e Fix unified SWA: size a non-owner's v2p by the id space it must address (#37560) Cheng WanandClaude Opus 5 2026-09-02 16:56:18 -07:00
• 5a1275a519 Converge the two SWA predicates, and stop conditioning the capture sink on the pool (#37550) Cheng WanandClaude Opus 5 2026-09-02 16:55:46 -07:00
• d9848b9ecd Build the unified read stream directly, without the page-table rectangle (#37512) Cheng WanandClaude Opus 5 2026-09-02 16:55:16 -07:00
• 18d5ffb42a Size the unified read-table grid from bs, and fuse the allocator's tombstone scatters (#37511) Cheng WanandClaude Opus 5 2026-09-02 16:54:26 -07:00
• c05f8ae830 [PD] Optimize paged allocator free-list release (#37146) 4 people 2026-09-03 07:51:37 +08:00
• 4bc34117f1 [CI] Install lmms-eval from PyPI, drop human-eval install, add clone token fallback (#37672) Liangsheng Yin 2026-09-02 16:23:10 -07:00
• a6da3a4922 [CI] Re-enable GB300 jobs (#37522) Alison Shao 2026-09-02 16:15:40 -07:00
• 718bd39fe0 [Fix] DP attention: correct the decode->extend prefix off-by-one (#37505) Mohammad Miadh Angkad 2026-09-03 07:14:16 +08:00
• 3fa6b86504 [Spec] Publish the final multi-layer EAGLE shared-read event (#36752) paulzhang-tmandQiaolin-Yu 2026-09-02 18:57:50 -04:00
• 19c30dff56 [SM120] DeepSeek-V4: DeepGEMM paged-MQA indexer +FP4 MoE+ page-split (#29927) eeechoandBaizhou Zhang 2026-09-03 06:49:59 +08:00
• 982aa8acfc [Bugfix] Load Qwen3.5 MTP embedding under PP (#37471) YAMY 2026-09-02 15:19:40 -07:00
• 3c9cea8f10 [EAGLE] Prune draft-extend logits to selected rows (#35546) YAMY 2026-09-02 15:10:08 -07:00
• fe45af1e6f perf(gdn): select ReplaySSM verify loop unrolling by shape (#36970) YAMY 2026-09-02 15:07:49 -07:00
• 9c70d22721 Update GLM-5.2 NVFP4 B200/B300 for AgentX HiCache (#35368) Faradawn Yang 2026-09-02 14:39:09 -07:00
• 3a855b050a fix(disagg): poll receivers during decode preallocation (#37483) cctry 2026-09-02 14:26:40 -07:00
• ad6e830858 [Bugfix] Key CUDA graph dedup signatures on kernel function identity (#37657) cctry 2026-09-02 14:24:31 -07:00
• 19c7679e9e [mem_cache] Make free_swa sync-free on page_size == 1 (#36723) Liangsheng Yin 2026-09-02 14:18:22 -07:00
• acea43079f Fix native MoE handling of noncontiguous top-k IDs (#36407) JoeandBBuf 2026-09-02 17:16:19 -04:00
• 2d799c28f4 [CI] Authenticate and retry git clones in install scripts (#37647) Liangsheng Yin 2026-09-02 13:21:26 -07:00
• f8cbf000f4 [AMD] Enable FP4 indexer for Deepseek V4 (#37353) 4 people 2026-09-02 09:45:08 -07:00
• f6aed6ec53 [diffusion] doc: rewrite stale diffusion compatibility matrix (#36987) Mick 2026-09-02 23:42:54 +08:00
• f586654518 [diffusion] feat: support FastH3 (4-step VSA-distilled MiniMax-H3) with a VSA-H3 attention backend (#37480) Kevin MiandClaude Fable 5 2026-09-02 06:39:54 -07:00
• 99b9109553 [AMD] Run ROCm 7.0 shadow tests every two days- #37582 (#37586) YC Yen-Ching TsengandChen 2026-09-02 11:51:16 +02:00
• 862a909a08 [Fix] Lock PP dynamic-chunk profiling requests before releasing through the tree cache (#37509) Liangsheng Yin 2026-09-02 02:09:01 -07:00
• ebfd8c60e5 [CI] Install sgl-eval from PyPI through the test extra (#37504) Liangsheng Yin 2026-09-02 01:45:25 -07:00
• fe3d4b9bbb fix: restore missing get_component_forced_attn_backend import in minimax_h3 (#37566) Shuwen WangandClaude Opus 5 2026-09-02 15:58:31 +08:00
• 4b329482e8 [diffusion] feat: support cube sparse attention for minimax h3 (#34893) 3 people 2026-09-02 15:21:33 +08:00
• 9175590aa0 [diffusion] refactor: admit explicit attention backends by capability (#37441) Mick 2026-09-02 15:17:57 +08:00
• d585cec4bd Fix nondeterministic FlashInfer GDN alignment test (#37343) Po-Han Huang (NVIDIA) 2026-09-02 14:46:58 +08:00
• f8f04bafa8 Rust server: align launcher and request validation behavior (#37327) Lianmin Zheng 2026-09-01 23:42:36 -07:00
• 83bd2c473f Allow custom policy for adaptive speculative decoding (#37274) jasonjk-park 2026-09-01 23:15:21 -07:00
• 2f03d305e9 [XPU] Add Regular Docker Image Release workflow for Intel XPU (#37340) Zaili Wang 2026-09-02 14:08:12 +08:00
• 01c3a5f54f [misc] Resolve SWA ownership at enqueue time for grouped free() (#36646) Liangsheng Yin 2026-09-01 23:06:55 -07:00
• 832d029870 [mem_cache] Split duplicate insert frees at the SWA eviction floor (#37481) Liangsheng Yin 2026-09-01 23:01:40 -07:00
• a6a19f9290 [Bugfix] Skip absent radix lock during cache cleanup (#37494) YAMY 2026-09-01 22:50:19 -07:00
• c66a285c94 [Kernel] GLM 5.3 Flash related kernels (ported from #36507) (#37477) Khoa PhamandClaude Opus 5 2026-09-01 22:17:09 -07:00
• 1109e44305 update CODEOWNERS (#37529) Mick 2026-09-02 12:19:11 +08:00
• ffd273bf4a Add polisettyvarma into CI_PERMISSION list (#37209) Zaili Wang 2026-09-02 11:44:24 +08:00
• a58751d54d [Fix ] Fix Spark2.5 hybrid SWA config (#37335) KnightYao 2026-09-02 11:29:09 +08:00
• 2d9c64394f Fix reasoning metrics and add TPOT to bench_multiturn (#35443) Wes 2026-09-02 11:28:47 +08:00
• 0157f1f552 [AMD][CI] Exclude unavailable MI355X nodes and skip 4N nightly (#37518) YC Yen-Ching TsengandChen 2026-09-02 05:06:54 +02:00
• d9ae1ebabd [CI] Preserve NCCL 2.30.7 after dependency installs (#37508) Mohammad Miadh Angkad 2026-09-02 10:59:13 +08:00
• 403a15c163 [CI] Batch CPU test workers (#37252) Xiaoyu Zhang 2026-09-02 10:35:14 +08:00
• 1aa8299d1d [Diffusion] Add cumulative extra-high quality tier (#37422) Xiaoyu Zhang 2026-09-02 10:26:13 +08:00
• 26f760d5c0 [CPU] Support FP8 KV cache (#32733) 3 people 2026-09-02 10:20:54 +08:00
• e874ae64cd [XPU][CI] Enable nightly-xpu-8-gpu suite: declare + wire runner job (#37230) ashwini rathiandP V R K Jyothendra Varma 2026-09-02 07:44:40 +05:30
• b83bf7a65f [Bugfix] Avoid scanning crash-dump token buffers during GC (#37297) Yongji WuandLianmin Zheng 2026-09-01 18:52:10 -07:00
• 22195709d1 [diffusion] refactor: remove component loader capability switches (#36824) Mick 2026-09-02 09:48:50 +08:00
• 66de38f30c Decouple ragged CUDA graph request and token capacities (#37300) Yichao Fu 2026-09-01 18:48:11 -07:00
• dde0ecdb90 [diffusion] feat: support spargeattention (#37437) Mick 2026-09-02 09:42:33 +08:00
• dc276264cb [AMD] Perf Kimi-K3 fuse ROCm KDA decode boundary (#34198) kkandwunhuang 2026-09-02 09:35:48 +08:00