 Wentao Ye
|
74c5cbcd7b
|
[Bugfix][MRV2][Spec Decode] Honor dynamic K in autoregressive speculators, 1.2~1.3x kernel perf improvement (#57053)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-10-05 14:54:11 -04:00 |
|
|
Raphaël RiallandandSimon Veitner
|
c32495d58f
|
[watermark] compatibility validation (#56801)
Signed-off-by: Raphael Rialland <raphael.rialland@mistral.ai>
Signed-off-by: Simon Veitner <sveitner@redhat.com>
Co-authored-by: Simon Veitner <sveitner@redhat.com>
|
2026-10-05 14:37:13 -04:00 |
|
|
aoshen02andClaude Opus 5.5
|
d09ff77637
|
[Bugfix] Give each data-parallel engine its own global RNG streams (#59788)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-05 17:38:18 +00:00 |
|
|
|
877ddcc456
|
[Bugfix][Spec Decode] Reserve the bonus KV slot for fill-in DSpark (#59105)
Signed-off-by: Evgeny Savinov <notime.sea@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Tomas Ruiz <tomas.ruiz.te@gmail.com>
|
2026-10-05 17:35:51 +00:00 |
|
|
akii96
|
182247257f
|
[ROCm][Perf] Use a stacked hipBLASLt GEMM for the bf16x3 router (#52668)
Signed-off-by: Aakif Nawaz <aakif.nawaz@amd.com>
|
2026-10-05 17:28:07 +00:00 |
|
|
Matthew BonanniandClaude Opus 5.5
|
54d93af9fb
|
[Bugfix][HiSparse] Reject cudagraph_mode=FULL at startup (#59688)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-05 12:42:27 -04:00 |
|
|
stefankoncarevicandAndreas Karatzas
|
87954c5b04
|
[CI/Build] Declare the video modality on the CohereCompass reference model (#60063)
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-10-05 16:25:42 +00:00 |
|
|
Mikko TukiainenandCursor
|
d23af12cb1
|
[ROCm][Perf] Reach the fused QSA pre-indexer from the AMD path (#57947)
Signed-off-by: mjkvaak-amd <mjkvaak-amd@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-10-05 16:22:29 +00:00 |
|
|
bzsuniandcjackal
|
528772a4bf
|
[Bugfix][Core] Retain encoder cache references for repeated multimodal inputs (#59942)
Signed-off-by: bzsuni <bingzhe.sun@daocloud.io>
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
Co-authored-by: cjackal <44624812+cjackal@users.noreply.github.com>
|
2026-10-05 15:52:46 +00:00 |
|
|
stefankoncarevic
|
f2d8fbf459
|
[CI/Build] Run the prefill token scoring test under batch invariance (#60056)
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com>
|
2026-10-05 10:32:33 -05:00 |
|
|
|
60932a6401
|
[Bugfix][Structured Output] Preserve literal values in Guidance disable_additional_properties (#58709)
Signed-off-by: Abhay Joshi <105213625+abhayjoshi201@users.noreply.github.com>
Co-authored-by: Antigravity <noreply@google.com>
Co-authored-by: Artem Perevedentsev <aperevedents@nvidia.com>
|
2026-10-05 18:12:40 +03:00 |
|
|
Nicolò Lucchesi
|
30d4032363
|
[Model][GLM-5.3-Flash] Support DCP for the kpool sparse indexer (#59211)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
|
2026-10-05 16:44:14 +02:00 |
|
|
Jee Jee Li
|
f9c9e8ac24
|
[LoRA] Remove tensorizer (#60024)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-10-05 07:01:56 -07:00 |
|
|
Abhay ShuklaandClaude Opus 5.5
|
d3547f9d03
|
[Test] Re-enable Voxtral HF reference test on Transformers v5 (#59771)
Signed-off-by: AbhayShuklaIIT <abhay.shukla@live.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-05 13:43:49 +00:00 |
|
|
cjackal
|
0e468adb43
|
[Model] Extend device-side mm normalization to Kimi K2.5 / K3 (#59278)
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
|
2026-10-05 21:28:13 +08:00 |
|
|
Nicolò LucchesiandLeoyzen
|
ff53f32409
|
[Attention][MLA] Support fp8_ds_mla KV cache for NoPE-512 models on SM90 (#59246)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
Co-authored-by: Leoyzen <leoyzen@gmail.com>
|
2026-10-05 13:12:00 +00:00 |
|
|
Vadim GimpelsonandClaude
|
d0d6e5f3a2
|
[Bugfix] Fix Mamba page size AssertionError with spec decoding on GraniteMoeHybrid, FalconH1 and Zamba2 (#59975)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-10-05 12:49:47 +00:00 |
|
|
roikoren755andmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
51eeb0c58f
|
[Bugfix] Load stacked expert weights for non-gated MoE (#59031)
Signed-off-by: Roi Koren <roik@nvidia.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-10-05 15:26:55 +03:00 |
|
|
Stefano CastagnettaandThien Tran
|
4ff028d77e
|
[Bugfix][Qwen4Exp] Honor --kv-cache-dtype-skip-layers in QSA attention (#60023)
Signed-off-by: Stefano Castagnetta <scastagnetta@nvidia.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
|
2026-10-05 12:13:30 +00:00 |
|
|
Juan Pérez de Algaba
|
710ac56e69
|
[Security] Restrict Pillow image formats on untrusted media paths (#60022)
Signed-off-by: Juan Pérez de Algaba <jperezde@redhat.com>
|
2026-10-05 10:40:15 +00:00 |
|
|
|
edca360f13
|
[Bugfix][Qwen4Exp] Load PLE tables unquantized under Quark checkpoints (#59443)
Signed-off-by: Mikko Tukiainen <Mikko.Tukiainen@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-10-05 10:40:02 +00:00 |
|
|
Maroon Ayoub
|
b1401e0aa7
|
[Bugfix][NIXL] Count heartbeats as remote engine activity (#59873)
Signed-off-by: Maroon Ayoub <mayoub@redhat.com>
|
2026-10-05 09:36:13 +00:00 |
|
|
|
ae53b06898
|
[Bugfix][GLM-5.3-Flash] Keep batch x heads out of gridDim.z in the GLM-5.3-Flash fused recurrent KDA kernel (#56974)
Signed-off-by: NolenLiang <nliang@nvidia.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-10-05 09:31:45 +00:00 |
|
|
aoshen02andClaude Opus 5.5
|
4a30c4cad0
|
[Model][DeepSeek-V4] Make MegaMoE shared-expert finalize independent of linear post-load order (#59927)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-05 08:39:49 +00:00 |
|
|
|
34051ad714
|
feat: Add video support for the Transformers backend (#57441)
pre-commit / pre-run-check (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Signed-off-by: Harshal Janjani <harshaljanjani@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-10-05 00:51:15 -07:00 |
|
|
|
042ab0305c
|
[Perf][Qwen4Exp] Merge QSA QKVG and indexer QK projections (#59533)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: namgyu-youn <namgyu.dev@gmail.com>
|
2026-10-05 07:03:29 +00:00 |
|
|
Thiago Mota MartinsandFangzhou Ai
|
92044241a0
|
[Bugfix][ROCm] Preserve config during GPU memory profiling (#58014)
Co-authored-by: Fangzhou Ai <31551580+Fangzhou-Ai@users.noreply.github.com>
|
2026-10-04 22:28:33 -07:00 |
|
|
|
e8a53a55e6
|
[Bugfix][Attention] Support int4_per_token_head on non-power-of-two head sizes (#56198)
Signed-off-by: Gawr Gura 0721 <LiRunGuo@users.noreply.github.com>
Co-authored-by: Gawr Gura 0721 <LiRunGuo@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-10-05 04:52:39 +00:00 |
|
|
Kam BasraandOpenAI Codex
|
0c16eee3f1
|
[Bugfix][KV Offload] Reset SimpleCPU eager-store placement state on MRV2 resume (#57816)
Signed-off-by: Kam Basra <kameldipbasra@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-10-05 02:00:07 +00:00 |
|
|
Vadim GimpelsonandClaude
|
4f52fa35ef
|
[Bugfix] Fix Qwen4Exp PLE embedding rejecting INC (AutoRound) checkpoints (#59990)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-10-05 01:52:06 +00:00 |
|
|
|
49e0f47978
|
[Bugfix][DSv4.1] Keep the compressor ring out of the null block (#58560)
Signed-off-by: bluemelov <hannes.b2411@eva.space>
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: bluemelov <hannes.b2411@eva.space>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-05 01:49:41 +00:00 |
|
|
|
1388100560
|
[Kernel][LoRA] Add deterministic split-K=8 LoRA shrink for batch invariance (#59377)
Signed-off-by: Shenglei Fu <117230642+ShengleiFu@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-10-04 18:46:16 -04:00 |
|
|
Stefan WangandRobert Shaw
|
b0eb87fe49
|
[Bugfix][Frontend] Return streaming errors before the first token (#40986)
Signed-off-by: 1fanwang <1fannnw@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-10-04 16:42:49 +00:00 |
|
|
|
89439db727
|
[CI][Docs] Fix decode/prefill consistency test prefix construction; add GLM-4-9B and Phi-4 to batch-invariant tested models (#53692)
Signed-off-by: Yifan Da <1363818765@qq.com>
Signed-off-by: LioEinaudi <zhao3024667639@gmail.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Yifan Da <1363818765@qq.com>
Co-authored-by: CodeBuddy <noreply@codebuddy.dev>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-10-04 11:55:18 -04:00 |
|
|
|
bd42276e1e
|
[Misc][Platform] Check aligned KV block sizes against every attention backend (#58457)
Signed-off-by: Divy <divy@coralbricks.ai>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-10-04 11:13:20 -04:00 |
|
|
Aarushi JainandAndreas Karatzas
|
bdd31c31de
|
[CI] Stop requiring both API servers to record weight sync metrics (#59521)
Signed-off-by: aarushjain29 <aarushi.jain2@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-10-04 14:14:27 +00:00 |
|
|
00CC
|
f98d1fc493
|
[ROCm][Bugfix] Fix ROCM_ATTN sliding-window boundary (#59550)
Signed-off-by: tangzzycc <3081129260@qq.com>
|
2026-10-04 13:48:46 +00:00 |
|
|
|
0872ddf4b9
|
[Bugfix][Multimodal] Normalize single-channel audio to 1D (#56691)
Signed-off-by: Ylean <61880605+Woolgathererer@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-10-04 06:11:41 +00:00 |
|
|
Zupeng Wang
|
18f8f96025
|
[Bugfix][KV Offload] Release pending CPU lookup pins on cache reset (#59862)
Signed-off-by: Wang Zupeng <zupenwang@gmail.com>
|
2026-10-04 04:30:17 +00:00 |
|
|
Yufeng HeandFlora Feng
|
6f75cc7d5d
|
[Bugfix][Responses API] Reuse streamed item ids in final harmony response (#59859)
Signed-off-by: Yufeng He <40085740+he-yufeng@users.noreply.github.com>
Signed-off-by: sfeng33 <4florafeng@gmail.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
|
2026-10-04 03:01:04 +00:00 |
|
|
Ting SUNandFlora Feng
|
50b404e71e
|
[Bugfix][Frontend] Preserve abort finish_reason for scale-out token streams (#47933)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
Signed-off-by: Flora Feng <4florafeng@gmail.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
|
2026-10-04 02:57:26 +00:00 |
|
|
Elvir Crnčević
|
ce49174247
|
[Bugfix] Fix FlashInfer all_reduce backend selection (#56891)
|
2026-10-03 22:18:58 -04:00 |
|
|
aoshen02andClaude Opus 5.5
|
5e56e9af2a
|
[Feature] Release the CUDA graph pool on sleep (#59160)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-04 01:13:10 +00:00 |
|
|
Harry Mellor
|
9e0b6fcf77
|
[CI] Bump Transformers version to 5.18.0 (#59621)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-10-04 00:42:35 +00:00 |
|
|
Wei Zhaoandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
84bcbc6264
|
[DCP] Enable TokenSpeed MLA with block-interleaved DCP (#59462)
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-10-03 17:26:07 +00:00 |
|
|
|
4ac0d0eac2
|
[ROCm][RDNA3] Fix W4A16 split-K accuracy and determinism (#54706)
Signed-off-by: AIwork4me <AIwork4me@users.noreply.github.com>
Co-authored-by: AIwork4me <AIwork4me@users.noreply.github.com>
Co-authored-by: JartX <sagformas@epdcenter.es>
|
2026-10-03 23:44:17 +08:00 |
|
|
Hexiang WangandCodex
|
f03026a548
|
[Bugfix][MoRIIO] Keep discovery heartbeats running while workers hold the GIL (#59441)
Signed-off-by: whx-sjtu <xiaowang990929@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-10-03 14:55:18 +00:00 |
|
|
|
e319f86f15
|
[Feature] Per-row candidate IDs for prefill token scoring (M2 of #56860) (#56984)
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-03 14:17:09 +00:00 |
|
|
Martin Hickey
|
bc21cba967
|
[Frontend] Add output_mode to /inference/v1/generate (RFC #56851 Phase 1) (#58588)
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
|
2026-10-03 19:38:25 +08:00 |
|
|
Yicong Wang
|
5f30fc7031
|
[Bugfix][KV Connector][Mooncake] Suppress completion for empty pulls (#59347)
Signed-off-by: wangyicong <wangyicong@bytedance.com>
|
2026-10-03 15:28:00 +08:00 |
|