 Qiaolin Yu
|
82fe0f041a
|
Fix stale flashinfer-MLA fallback poisoning spec verify capture (trtllm_mla + tc_piecewise) (#32288)
|
2026-07-24 13:24:26 -07:00 |
|
|
Zheng Wengang
|
be7c13af07
|
[BugFix] Fix DS/Kimi crash on non-first PP ranks when resolving input length (#31752)
|
2026-07-24 12:19:02 -07:00 |
|
|
mosya415andmosya415
|
71015f3fea
|
fix(dsa): fail fast on fp8_e4m3 KV with tilelang DSA backend on CUDA (#31346)
Co-authored-by: mosya415 <263250241+mosya415@users.noreply.github.com>
|
2026-07-24 12:10:38 -07:00 |
|
|
Jinyan Chen
|
1e69765bae
|
Add FP4 Indexer for DeepSeek V4 on SM120 (#27059)
|
2026-07-24 11:37:23 -07:00 |
|
|
YAMY
|
2428f56145
|
[Bugfix] Fix Kimi-Linear state transfer across heterogeneous TP (#32262)
|
2026-07-24 10:31:17 -07:00 |
|
|
Zhiqiang Xie
|
5da0b6ec39
|
Write-back policy fix for unified tree (#31845)
|
2026-07-24 09:58:18 -07:00 |
|
|
Lu Fang
|
448662e85e
|
[mm] Accept per-item embedding lists from DataEmbeddingFunc (#31826)
|
2026-07-24 08:27:24 -07:00 |
|
|
khalilzhk
|
dfaf75b1a6
|
[NPU] bugfix for extra device memory on Ascend (#30112)
|
2026-07-24 21:13:21 +08:00 |
|
|
|
3d91a569ce
|
[MoE Backend] Add HPC-Ops FP8 MoE runner backend (#30541)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Halcyon <56064364+VAthree@users.noreply.github.com>
|
2026-07-24 19:46:11 +08:00 |
|
|
Jun LiuandXiaoyu Zhang
|
4d5917e744
|
Add DeepSeek-reference 1e-20 epsilon to top-k renormalization to prevent 0/0 NaN (#31017)
Co-authored-by: Xiaoyu Zhang <1182563586@qq.com>
|
2026-07-24 19:45:44 +08:00 |
|
|
|
8389d79e43
|
ci: add LongCat-Flash-Lite-FP8 8-GPU nightly test + fix NextN rope_theta (#32125)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Xiaoyu Zhang <1182563586@qq.com>
|
2026-07-24 19:45:28 +08:00 |
|
|
|
841fa293b5
|
[Fix] Reject online weight updates while the HPC-Ops router GEMM split cache is active (#31943)
Co-authored-by: Halcyon <56064364+VAthree@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-24 19:30:13 +08:00 |
|
|
Liangsheng Yin
|
a31542ebd9
|
[Feature] Add leveled invariant-check primitive for nan/inf/oob validity checks (#32308)
|
2026-07-24 04:27:20 -07:00 |
|
|
YAMY
|
de816e1eb5
|
[Disagg][StagingBuffer][1/2] Robustness and failure handling (#31217)
|
2026-07-24 17:22:55 +08:00 |
|
|
Liangsheng Yin
|
f4f15162bc
|
[Fix] Fail fast when a safetensors index references missing shard files (#32279)
|
2026-07-24 02:18:56 -07:00 |
|
|
Yuzhen Zhou
|
b954e9cf3d
|
[6/6][kimi-deterministic] Use deterministic seeded coins for EAGLE rejection sampling (#30822)
|
2026-07-24 02:11:21 -07:00 |
|
|
Zheng Wengangandsiyu
|
364b5f23e6
|
[BugFix][EPD] Harden zmq_to_scheduler receiver failures; sync error info across TP (#31592)
Co-authored-by: siyu <liusy58@linux.alibaba.com>
|
2026-07-24 16:37:52 +08:00 |
|
|
Jun LiuandXinyuan Tong
|
58f417049d
|
[PD] Fix multi-tokenizer disaggregation metrics labels (#30412)
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
|
2026-07-24 16:27:21 +08:00 |
|
|
Sam Shleifer
|
b8bb1b4e5a
|
[lora] Fix WAR race: never write MoE runner output into hidden_states in place (#31870)
|
2026-07-24 00:58:55 -07:00 |
|
|
Liangsheng Yin
|
d059b0f56e
|
[Fix] Clamp degenerate all-sentinel draft rows to token 0 in dspark _online_combine_kernel (#32277)
|
2026-07-24 00:53:56 -07:00 |
|
|
|
35e25f5356
|
[Feature] DCP: A2A + FlashInfer-MNNVL comm backends and q-replicate (Helix) (#21637)
Co-authored-by: Hao Phan <htphan@nvidia.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: kpham-sgl <khoa.pham@radixark.ai>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
|
2026-07-24 00:21:53 -07:00 |
|
|
Xinyuan Tong
|
39955d5314
|
[MoE] Make DeepEP auto serve flashinfer_cutedsl FP4 (coerce to low_latency) + guard (#29523)
|
2026-07-24 06:59:18 +00:00 |
|
|
Qiaolin Yu
|
15d73f1e03
|
Fix dynamo recompile limit in allreduce and bf16 gemm (#32239)
|
2026-07-23 22:24:01 -07:00 |
|
|
Polisetty V R K Jyothendra VarmaandMa Mingfei
|
319055c191
|
[Intel GPU] Add XPU Platform support (#31949)
Signed-off-by: P V R K Jyothendra Varma <polisetty.v.r.k.jyothendra.varma@intel.com>
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
|
2026-07-24 12:49:29 +08:00 |
|
|
ANSHUMAN TRIPATHY
|
f0f78a6c93
|
Add deterministic inference for eagle parity test (#30026)
|
2026-07-24 12:48:21 +08:00 |
|
|
Liangsheng Yin
|
99b29bf188
|
[Fix] Support ENCODER_ONLY target-verify in the trtllm_mha backend (#32178)
|
2026-07-23 20:33:39 -07:00 |
|
|
Cheng Wan
|
eac7c7d7cd
|
fix(attention): read per-runner kv cache dtype off model_runner (#32251)
|
2026-07-23 20:08:57 -07:00 |
|
|
|
1e10ec93b3
|
[XPU] Add XPU device support for LMCache radix cache integration (#23534)
Co-authored-by: Christopher Manteuffel <christopher.manteuffel@intel.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
|
2026-07-24 08:41:01 +08:00 |
|
|
Polisetty V R K Jyothendra VarmaandMa Mingfei
|
2f823a2eee
|
[Intel GPU] calculate free memory based on allocated memory for XPU (#32044)
Signed-off-by: P V R K Jyothendra Varma <polisetty.v.r.k.jyothendra.varma@intel.com>
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
|
2026-07-24 08:38:52 +08:00 |
|
|
Yihao Wang
|
433429b16a
|
diffusion: skip _save_gt_output for 3d/mesh (#32117)
|
2026-07-24 08:14:05 +08:00 |
|
|
Xiaoyu ZhangandClaude Fable 5
|
d4a0dfbc31
|
[Fix] Two root causes of the H100 deepep TBO CI break: scale-tensor use-after-free + missing non-finite quant sanitization (#32188)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-24 07:29:28 +08:00 |
|
|
Liangsheng Yin
|
59ef3b15cc
|
[Fix] Reserve the mamba pool's +1 padding slot in the memory budget solve (#32184)
|
2026-07-23 14:55:35 -07:00 |
|
|
Baizhou Zhang
|
3d0c6bf57f
|
[Fix] Fix trtllm_mla backend + fp8 kv cache without rope (#32181)
|
2026-07-23 14:55:18 -07:00 |
|
|
Qiaolin Yu
|
a0728ea502
|
[spec decoding] fix inkling multi layer mtp draft extend cuda graph (#32254)
|
2026-07-23 14:52:30 -07:00 |
|
|
Siyuan Chen
|
71fe41b6b3
|
[DSV4] Support megamoe for CP (#29569)
|
2026-07-23 14:46:32 -07:00 |
|
|
Qiaolin Yu
|
378aea1385
|
Fix nvfp4 online scale with pcg (#32246)
|
2026-07-23 14:42:37 -07:00 |
|
|
Jimmy Shong
|
410ab4fde5
|
Add return_token_ids support to completions and chat completions APIs (#30917)
|
2026-07-23 14:41:52 -07:00 |
|
|
Yongfei Xu
|
ebe3ab29e4
|
[DeepSeek V4] CP decode opt: slice repeat attention weights to local TP partition (#27657)
|
2026-07-23 14:06:25 -07:00 |
|
|
Mohammad Miadh Angkad
|
a2ddf92e61
|
[CI] Fix Mamba ServerArgs namespace (#32211)
|
2026-07-23 13:15:50 -07:00 |
|
|
Sam Shleifer
|
1f9d778d1b
|
Skip dist_init/nccl port prechecks when the dist init method is overridden (#31410)
|
2026-07-23 12:40:41 -07:00 |
|
|
Rain Jiang
|
7fe82dd02e
|
create rust workspace (#32014)
|
2026-07-23 12:02:41 -07:00 |
|
|
Hongkuan Zhou
|
d0b9689805
|
[Fix] Include disagg prefill waiting queue in FPM (#32122)
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
|
2026-07-23 09:30:27 -07:00 |
|
|
Jialin Ouyangandhzh0425
|
70ac0c4b0e
|
[UnifiedRadixCache][mamba] Fix mamba state corruption and slot leak when load_back aborts (#30986)
Co-authored-by: hzh0425 <hzh0425@apache.org>
|
2026-07-23 18:48:31 +08:00 |
|
|
YAMY
|
c18919f8f3
|
[Mamba] Add a per-path cap for cached states (#31230)
|
2026-07-23 17:58:36 +08:00 |
|
|
Xiaoyu ZhangandClaude Opus 4.8
|
62aa85d9aa
|
[Kernel] Sweep missed dedicated kernels into kernels.ops (moe/quant siblings + dspark) (RFC #29630) (#32160)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-07-23 17:07:16 +08:00 |
|
|
Liangsheng Yin
|
f35411ee81
|
[Spec] Enable grammar overlap scheduling for STANDALONE speculative decoding (#32110)
|
2026-07-23 01:47:27 -07:00 |
|
|
Liangsheng Yin
|
9b853e6832
|
[Scheduler] Enable decode retraction ordering under speculative decoding (#32023)
|
2026-07-23 00:42:56 -07:00 |
|
|
heziiop
|
235a488c87
|
[NPU] ascend fuseep use moe ep group (#32040)
|
2026-07-23 14:07:14 +08:00 |
|
|
silencejade
|
09071be105
|
[NPU] [FIX] Fix performance degradation of Qwen3.5-397B-A17B (#32130)
|
2026-07-23 14:05:10 +08:00 |
|
|
Xiaoyu ZhangandClaude Opus 4.8
|
11b0e5c5ad
|
[Kernel] Classification cleanup: unify _jit_ naming, drop empty/model groups, add elementwise (RFC #29630) (#32148)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-07-23 13:47:02 +08:00 |
|