|
ca0df1f122
|
[Bugfix][Core] Exempt exactly the blocks an async KV load writes from zeroing (#59504)
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-10-03 06:26:12 +00:00 |
|
|
Nils Matteson
|
28556f8600
|
[Bugfix] Log CRIU failure details before snapshot cleanup (#59661)
Signed-off-by: Nils Matteson <nilsmatteson@icloud.com>
|
2026-10-03 04:02:27 +00:00 |
|
|
Nils Matteson
|
9fdb174678
|
[Bugfix] Avoid InfiniBand state in TP1 snapshots (#59699)
Signed-off-by: Nils Matteson <nilsmatteson@icloud.com>
|
2026-10-03 03:59:17 +00:00 |
|
|
Divakar Verma
|
faa9860dbd
|
[ROCm][CI][AiterExperts] Add test coverage for hidden/intermediate padding correctness (#59333)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-10-03 01:53:37 +00:00 |
|
|
C
|
44198f577f
|
[Bugfix][Model] Fix M-RoPE offset double-count in Qwen3-Omni (#58890)
Signed-off-by: C1ves <3121985758@qq.com>
|
2026-10-03 09:00:51 +08:00 |
|
|
DOCCA0andRobert Shaw
|
7dfe3338d5
|
[EPLB] Add contention-aware expert migration batching (#52641)
Signed-off-by: DOCCA0 <2947323341@qq.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-10-03 00:13:50 +00:00 |
|
|
Wentao Ye
|
8bdd8d847d
|
[GLM 5.3 Perf] Enable fused multi-step decode, 13.3% E2E throughput improvement for concurrency 1 (#57443)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-10-02 20:05:27 -04:00 |
|
|
Ayaan Nadamal
|
84593955fa
|
[Perf][MoE] Support fp8 combine in FlashInfer one-sided MoE all2all (#57995)
Signed-off-by: Ayaan Nadamal <anadamal@nvidia.com>
|
2026-10-02 16:29:16 -04:00 |
|
|
Julien Debache
|
111f71a6db
|
[feat] FlashInfer CuteDSL MegaMoE integration (#54049)
Signed-off-by: jdebache <jdebache@nvidia.com>
|
2026-10-02 15:43:33 -04:00 |
|
|
Benedikt Falk
|
c4973d94fe
|
[Bugfix][Frontend] Avoid generation for empty streaming input (#59015)
Signed-off-by: Benedikt Falk <bfalk@nvidia.com>
|
2026-10-02 18:48:43 +00:00 |
|
|
simon-veitner-redhatandLucas Wilkinson
|
202d497aa8
|
[Bugfix][Watermarking] Keep draft prompt lengths valid under CUDA graphs (#59779)
Signed-off-by: Simon Veitner <sveitner@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
|
2026-10-02 14:32:11 -04:00 |
|
|
Shijin ZhangandFlora Feng
|
d1a974c140
|
[Frontend] Constrain non-strict GLM-4.7 tool calls with a shallow structural tag (#56403)
Signed-off-by: Shijin Zhang <75300765+Dovis01@users.noreply.github.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
|
2026-10-02 14:31:53 -04:00 |
|
|
Wentao Ye
|
f700178f90
|
[Refactor] Remove dead env and config (#59781)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-10-02 18:07:20 +00:00 |
|
|
Wentao Ye
|
4e4d75c459
|
[GLM5.3 Perf] Reuse sparse MLA index conversion across layers, 3.5~3.9x kernel performance improvement (#59464)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-10-02 17:37:45 +00:00 |
|
|
Thang NguyenandClaude Opus 5.5
|
7cfd233538
|
Revert "[Bugfix] Tie lm_head.weight for Nemotron Parse when checkpoint omits it" (#53020) (#59805)
Signed-off-by: Thang Nguyen <thangnguyenvn647@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-02 10:19:25 -07:00 |
|
|
Stefano CastagnettaandBenjamin Chislett
|
f590eb2448
|
[Perf][Qwen4Exp] Add SM121 TP=1 skinny-GEMM plans (#59753)
Signed-off-by: Stefano Castagnetta <scastagnetta@nvidia.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-10-02 17:17:45 +00:00 |
|
|
|
9cf087fd14
|
[Perf] Tune MoE weighted-sum kernel launch configuration (#59731)
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
|
2026-10-02 17:09:29 +00:00 |
|
|
Misha GoinandClaude
|
1ab18599ca
|
[Agents] Add pre-commit check for agent files and skills (#59657)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-10-02 09:38:22 -07:00 |
|
|
rmhaskarandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
e42d35d4f3
|
[Minimax-M3] Keep the native FP8 MMA in the Triton indexer scorers (#59481)
Signed-off-by: Rajas Mhaskar <rmhaskar@nvidia.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-10-02 12:30:39 -04:00 |
|
|
djramic
|
167a81fa9c
|
[CI] Fix ModelExpress handling in weight transfer tests (#59772)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
|
2026-10-02 11:30:01 -05:00 |
|
|
Divakar Verma
|
6abadc2aa7
|
[ROCm][CI] Add test coverage for VLLM_ROCM_MOE_PADDING memory-stride padding transparency (#59332)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-10-02 11:23:22 -05:00 |
|
|
Divakar Verma
|
2a537887de
|
[CI] Use vllm_runner in fusions_e2e conftest for reliable GPU cleanup (#59525)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-10-02 11:21:21 -05:00 |
|
|
|
4c4003bb5f
|
[Bugfix] Bind routed-experts capture to the MoE layer, not the kernel (#59455)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-02 15:50:38 +00:00 |
|
|
|
592c6f3fbc
|
[Bugfix][Pooling] Handle multimodal cache misses without crashing (#58975)
Signed-off-by: linchaoying6 <linchaoying6@jd.com>
Co-authored-by: linchaoying6 <linchaoying6@jd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-10-02 10:14:33 -04:00 |
|
|
tenotekandClaude Fable 5.1
|
443dccd3c9
|
[Bugfix][Multimodal] Fix reference counting of the SHM processor cache (#59695)
Signed-off-by: tenotek <50898317+hdq66666@users.noreply.github.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-10-02 22:14:13 +08:00 |
|
|
|
e4294144a8
|
[Perf] Keep non-speculative GDN decode on the standard path (#59735)
Signed-off-by: DimensionSTP <65501090+DimensionSTP@users.noreply.github.com>
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: Kimi Code <noreply@moonshot.ai>
|
2026-10-02 13:44:53 +00:00 |
|
|
Jiangyun ZhuandClaude Opus 5.5
|
d648847fe4
|
[CI][Kimi-K3] Test prefix cache reuse with KV offload, P/D and DCP (#59229)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-02 20:58:35 +08:00 |
|
|
Stefano CastagnettaandClaude Opus 5
|
f0b4b36890
|
[Bugfix][Quantization] Detect NVFP4 in ModelOpt mixed-precision checkpoints (#56050)
Signed-off-by: Stefano Castagnetta <scastagnetta@nvidia.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-10-02 12:30:22 +00:00 |
|
|
Abhay ShuklaandClaude Opus 5.5
|
fa212b8dc5
|
[Test] Re-enable Ovis2.5 and Ovis2.6-MoE vLLM tests on Transformers v5 (#59763)
Signed-off-by: AbhayShuklaIIT <abhay.shukla@live.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-02 11:59:40 +00:00 |
|
|
Harry MellorandClaude Opus 5.5
|
5d20979fc9
|
[Misc] Remove code paths for Transformers < 5.16.1 (#59762)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-02 11:17:24 +00:00 |
|
|
|
8c60714da5
|
[Bugfix][LoRA] Fall back for high-rank MoE LoRA (#55161)
Signed-off-by: Raina Zhong <yuweiz@nvidia.com>
Co-authored-by: Raina Zhong <yuweiz@nvidia.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-10-02 13:59:28 +03:00 |
|
|
Simon Danielssonandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
98b29aa99a
|
[ROCm][Perf][GLM-5.3-Flash] Add AITER topk backend for decodes (#58167)
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-10-02 11:47:41 +01:00 |
|
|
Simon Danielssonandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
751fa96a49
|
[ROCm][Perf][GLM-5.3-Flash] Remove redundant copy after ragged sparse MLA (#58569)
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-10-02 11:45:51 +01:00 |
|
|
|
5688a4dd4a
|
[Bugfix][GLM-5.3] Size the image encoder cache from the exact token ceiling (#59565)
Signed-off-by: Yufeng He <40085740+he-yufeng@users.noreply.github.com>
Co-authored-by: Kimi Code <kimi-code@moonshot.cn>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-10-02 10:43:29 +00:00 |
|
|
|
af2a582d5c
|
[Bugfix][Spec Decode] Qualify Transformers backend attention layer names with the model prefix (#59293)
Signed-off-by: Farhad Al-Amin <99006654+Legend-2727@users.noreply.github.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-10-02 11:21:20 +01:00 |
|
|
aoshen02andClaude Opus 5.5
|
8e58ac22af
|
[Feature] Offload KV-init runtime state on sleep (#59158)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-02 09:49:21 +00:00 |
|
|
Juan Pérez de Algaba
|
c15672cfb4
|
[Security] Accept zero-sum DeepSeek-OCR pixel tensors (#59417)
Signed-off-by: Juan Pérez de Algaba <jperezde@redhat.com>
|
2026-10-02 09:17:12 +00:00 |
|
|
|
9d2a6f52b2
|
[Rust Frontend] Expose gRPC port in Python vllm serve (#59659)
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Alec Flowers <aflowers@nvidia.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-10-02 08:14:37 +00:00 |
|
|
kliuae
|
0154979656
|
[ROCm][Perf] Kimi-K3 enable prefill checkpoints on ROCm (#58344)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
|
2026-10-02 06:58:04 +00:00 |
|
|
|
4056c8ac1f
|
[Bugfix][HiSparse] Fix MTP acceptance collapse under FULL graphs with a saturated GPU pool (#59309)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
|
2026-10-01 23:04:21 -07:00 |
|
|
|
f7999d2e44
|
[Bugfix][HiSparse] Size the KV cache from the groups HiSparse allocates (#59450)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
|
2026-10-02 04:11:55 +00:00 |
|
|
Qiu ChunshuoandLucas Wilkinson
|
8486f1ebfe
|
[Perf][PCP] Shard decode requests across PCP ranks (#52162)
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
|
2026-10-01 23:50:13 -04:00 |
|
|
|
a810316c08
|
[Bugfix] Keep batch-invariance NCCL pins out of the weight-transfer group (#59500)
Signed-off-by: aoshen524 <aoshen524@gmail.com>
Co-authored-by: aoshen524 <aoshen524@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
|
2026-10-02 11:19:28 +08:00 |
|
|
Martin Hickey
|
fcfacc3499
|
[Bugfix][Frontend] Seed derender detokenization from the prompt (#59046)
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
|
2026-10-02 03:17:56 +00:00 |
|
|
Prudhvi VudaandOpenAI Codex
|
ea106db806
|
[Bugfix][Bench] Clean up synthetic video files and writers (#59529)
Signed-off-by: Prudhvivuda <prudhvi12042001@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-10-02 02:51:34 +00:00 |
|
|
|
9bd993564f
|
[Frontend] Parse tool calls and reasoning from checkpoint response templates (#58604)
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Yoni Gozlan <yonigozlan@users.noreply.github.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-10-02 02:33:00 +00:00 |
|
|
Hyunjae Wooandaoshen02
|
5a661487e2
|
[Feature] Add native ModelExpress weight transfer backend (#58399)
Signed-off-by: Hyunjae Woo <hwoo@nvidia.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
|
2026-10-02 02:29:35 +00:00 |
|
|
Flora Feng
|
785b990116
|
[Distributed] Enable custom all-reduce under VLLM_BATCH_INVARIANT (#58623)
Signed-off-by: Flora Feng <4florafeng@gmail.com>
Signed-off-by: sfeng33 <4florafeng@gmail.com>
|
2026-10-02 02:25:48 +00:00 |
|
|
Harry MellorandClaude Opus 5
|
e3cae8d2ac
|
[Model] Use upstream GLM-5.3 and Qwen4-Exp configs and processor (#57387)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-10-02 02:25:18 +00:00 |
|
|
aoshen02andClaude Opus 5.5
|
866f02db8a
|
[Feature] Release WorkspaceManager scratch on sleep (#59156)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-02 02:14:37 +00:00 |
|