 gongwei-130andClaude Fable 5.1
|
34e104f6fe
|
[gRPC] Fix ping tolerance so long non-streaming RPCs are not dropped (#55102)
Signed-off-by: Wei Gong <wei@together.ai>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-09-25 02:14:32 +00:00 |
|
|
Divakar Verma
|
65c5e24689
|
[ROCm][CI][AITER Coverage] Harden MoE sorting-backend/dispatch env-var test matrix (#58393)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-09-24 21:14:02 -05:00 |
|
|
김재억
|
32fc82343f
|
[Bugfix][LogitsProcessor] Validate ':' separator in custom logits processor FQCN (#56020)
Signed-off-by: 100milliongold <gadian88@gmail.com>
|
2026-09-25 01:49:20 +00:00 |
|
|
Juntian Liu
|
609731e8f5
|
[Perf][DSv4.1] Restore the fused query RMSNorm + MXFP8 quantization path (#57679)
Signed-off-by: Juntian Liu <Juntianl777@gmail.com>
|
2026-09-25 01:39:03 +00:00 |
|
|
|
3652f35e7c
|
[Bugfix][Quantization] Refresh online NVFP4 scales before reload post-processing (#57954)
Signed-off-by: S1ro1 <matej.sirovatka@gmail.com>
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
|
2026-09-24 18:36:08 -07:00 |
|
|
|
16070ed7e9
|
[Minimax-M3][Perf] Use triton_mrope for vision tower + int64 offset fix for triton_mrope (#58526)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: Kimi <noreply@moonshot.cn>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-09-24 18:30:32 -07:00 |
|
|
Thien Tran
|
ade1056ee5
|
[Kimi-K3][Perf] Dispatch GEMM for vision patch embedder (#58527)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
|
2026-09-24 18:30:11 -07:00 |
|
|
Nick HillandClaude Opus 5.5
|
7dbd0a8d22
|
[Bugfix][MRV2] Treat padded prompt tails as spec-decode rows for hybrid models (#58434)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
|
2026-09-24 18:29:53 -07:00 |
|
|
|
155b988373
|
[CI] Run DFlash2 NVFP4 acceptance test on B200; skip it on H200 35GB MIG (#58496)
Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
|
2026-09-24 19:29:44 -06:00 |
|
|
Samuel KimandClaude
|
34ee85d5ca
|
[Perf] Batch Mamba2 prefill SSM state saves, removing GPU<->CPU syncs (#49371)
Signed-off-by: samuelkim7 <samuelmwkim@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-09-25 01:11:19 +00:00 |
|
|
SIDDARTHA REDDY
|
a811738a60
|
[Bugfix] Accept EOS after grammar finish in outlines backend; reject json_object at validation (#57743)
Signed-off-by: SIDDARTHA REDDY <75976672+SIDDARTHAREDDY8@users.noreply.github.com>
|
2026-09-24 17:17:10 -07:00 |
|
|
Yifan QiaoandClaude Fable 5.1
|
39724758e7
|
[Bugfix] GLM-5.3-Flash: launch the kpool paged MQA logits in the varlen mode its schedule was built with (#55270)
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-09-25 00:13:55 +00:00 |
|
|
Samyabrata MajiandFlora Feng
|
064bc747ab
|
[Bugfix][Frontend] Count reasoning tokens for Harmony, DeepSeek-V3 and Step3 parsers (#58626)
Signed-off-by: Samyabrata Maji <116789799+sammaji@users.noreply.github.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
|
2026-09-25 00:12:29 +00:00 |
|
|
|
b3a87b2d04
|
[Bugfix][KVConnector] Finalize saves on steps without a forward (#57775)
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Kimi Code <noreply@moonshot.ai>
|
2026-09-25 00:06:36 +00:00 |
|
|
Khushali Desai
|
7833ff25dd
|
Release prompt_embeds tensor when its InputBatch slot is freed (#57988)
Signed-off-by: khushali9 <khushali.desai9@gmail.com>
|
2026-09-25 00:00:44 +00:00 |
|
|
|
7a9406690e
|
[KV Connector] Fix DecodeBench fp8 fill values and add a startup fill mode (#58472)
Signed-off-by: Zijing Liu <liuzijing2014@gmail.com>
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-24 23:55:47 +00:00 |
|
|
Misha GoinandCodex
|
71891bdb94
|
[Perf] Parallelize registered CUDA Triton kernel warmup at startup (#58582)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-24 19:52:00 -04:00 |
|
|
|
d5051abaf1
|
[Bugfix][Mamba] Restore prompt-tail prefix-cache hits with MTP (#58368)
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-09-24 23:46:42 +00:00 |
|
|
Misha Goin
|
4f72bd0152
|
[Bugfix][Quantization] Give LM heads standard linear metadata (#58444)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-09-24 16:39:49 -07:00 |
|
|
stefankoncarevicandAndreas Karatzas
|
9ac3b7c69f
|
[ROCm][CI] Mirror the DSv4-Flash disaggregated DP EP group on MI355 (#58558)
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-09-24 18:38:25 -05:00 |
|
|
|
f6aa2919bc
|
[Bugfix][Core] Keep every multimodal feature in the partial-block KV event (#58288)
Signed-off-by: haosenwang1018 <haosenwang1018@users.noreply.github.com>
Co-authored-by: haosenwang1018 <haosenwang1018@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-09-24 23:25:01 +00:00 |
|
|
Miłosz Grunwald
|
bd4cb3fe4e
|
[BUGFIX] fix ovis2_5 multimodal tokens (#52623)
Signed-off-by: Milosz Grunwald <milosz.grunwald@intel.com>
|
2026-09-25 07:18:54 +08:00 |
|
|
snadampalandNicolò Lucchesi
|
6a86bf626e
|
[PD][PushConnector] Record last activity of remotes on the D side (#52245)
Signed-off-by: Sunita Nadampalli <nadampal@amazon.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@mistral.ai>
|
2026-09-24 23:15:32 +00:00 |
|
|
Andrey Talman
|
f5b40fcdfe
|
[CI] Report to CRCR after all jobs finish, gated on the build's long pole (#58628)
|
2026-09-24 16:02:30 -07:00 |
|
|
Fanli LinandKunshang Ji
|
7edb27f68e
|
[XPU][CI] enable prompt embeds tests on XPU (#58283)
Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
Signed-off-by: Fanli Lin <fanli.lin@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-09-25 06:56:59 +08:00 |
|
|
Jellow
|
e6c07ea576
|
[Bugfix][KV Cache] Fix incremental multimodal block hashing (#51694)
Signed-off-by: Jellow <49915976+CZT0@users.noreply.github.com>
Signed-off-by: Jellow <dvdx@foxmail.com>
|
2026-09-24 15:38:03 -07:00 |
|
|
Nick Hill
|
36f94d5fe8
|
[Bugfix][Outlines] Fix EOS termination and unconstrained masks after rejected drafts (#58612)
|
2026-09-24 21:55:56 +00:00 |
|
|
Juntian LiuandClaude Opus 5.5
|
04730e8270
|
[DFlash] Capture the context K/V precompute in the draft CUDA graph (#57632)
Signed-off-by: Juntian Liu <Juntianl777@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
|
2026-09-24 21:38:04 +00:00 |
|
|
stefankoncarevicandAndreas Karatzas
|
e33de821c0
|
[ROCm][CI] skip the ROCm MRV1 default where MRV1 cannot serve the config (#58535)
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-09-24 15:36:36 -05:00 |
|
|
Aaron KangandMisha Goin
|
0908116dd9
|
[Bugfix] Pass quant_config to DiffusionGemma's ParallelLMHead (#48521)
Signed-off-by: Aaron Kang <aaron.h.kang@icloud.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
|
2026-09-24 13:17:02 -07:00 |
|
|
|
ab3de6edf2
|
[Perf] DiffusionGemma: constrained reads over the request's logprob_token_ids (#58216)
Signed-off-by: Matt Mastracci <matthew@mastracci.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
|
2026-09-24 13:15:08 -07:00 |
|
|
|
92e9c6bf13
|
[ROCm] Fix misrouting race-condition in multi-decode P/D disagg with mori-io (#51681)
Signed-off-by: Vincent Cave <vincent.cave@amd.com>
Signed-off-by: Shiksha Patel <shikpate@amd.com>
Co-authored-by: Shiksha Patel <shikpate@amd.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-09-24 19:52:43 +00:00 |
|
|
|
90a9515006
|
[Cleanup] Remove online quantization support in fp8.py in favor of online shorthands (#53585)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-24 12:48:14 -07:00 |
|
|
Misha Goin
|
58aa2f1ef1
|
[Refactor] Move auxiliary files out of the repository root (#58572)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-09-24 12:38:56 -07:00 |
|
|
Misha Goin
|
cd06e81c41
|
[Bugfix][Quantization] Add Humming to the W4A8 (INT4xFP8) MoE oracle (#58427)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-09-24 12:37:33 -07:00 |
|
|
Xun Sun
|
e773247f8a
|
[Fast Start] Wait for weight cache daemon readiness (#58370)
|
2026-09-24 19:18:04 +00:00 |
|
|
Nick HillandKimi Code
|
e30559b58f
|
[Core] Skip JIT monitor when JIT warmup is disabled (#58590)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Kimi Code <noreply@moonshot.cn>
|
2026-09-24 12:08:16 -07:00 |
|
|
Nick HillandKimi
|
074d57fce1
|
[Bugfix] Keep JIT warmup under enforce-eager when fault tolerance is on (#58593)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Kimi <noreply@moonshot.cn>
|
2026-09-24 12:07:32 -07:00 |
|
|
|
5b3f280a6d
|
[Bugfix] Count unsplit Idefics3 image patches (#48760)
Signed-off-by: nightcityblade <nightcityblade@gmail.com>
Co-authored-by: nightcityblade <nightcityblade@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-09-24 11:36:26 -07:00 |
|
|
Thomas OrtnerandHarry Mellor
|
8b84e15066
|
[transformer] RMSNorm matching for alternative rsqrt (#54461)
Signed-off-by: Thomas Ortner <boh@zurich.ibm.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-09-24 16:33:06 +00:00 |
|
|
Nick Hill
|
09fe178dba
|
Revert "[DSpark] Support pipeline-parallel targets in aggregated serving (#56956)" (#58484)
|
2026-09-24 08:48:36 -07:00 |
|
|
Harry MellorandClaude Opus 5.5
|
d636456b1f
|
[Frontend] Remove the slow tokenizer mode (#58545)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
|
2026-09-24 08:48:28 -07:00 |
|
|
|
344fcc252a
|
[Bugfix] Resolve the Hub revision once per repo (#56092)
Signed-off-by: Wauplin <lucainp@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-24 08:48:24 -07:00 |
|
|
|
a7d203efe5
|
fix(config): apply presence_penalty/frequency_penalty from override-generation-config (#50769)
Signed-off-by: Chenglun Hu <chenglunhu@gmail.com>
Signed-off-by: hclsys <chenglunhu@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-09-24 08:48:18 -07:00 |
|
|
Yueh-Ting (eop) Chen
|
26f49e336a
|
[Perf][Attention] Bound FlashInfer prefill dequantization scratch (#57918)
Signed-off-by: Yueh-Ting Chen <yueh.ting.chen@gmail.com>
|
2026-09-24 10:42:08 -04:00 |
|
|
Wentao Ye
|
3c42385d7d
|
[Refactor] Remove dead or duplicate tests (#58446)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-09-24 10:29:56 -04:00 |
|
|
Harry MellorandClaude Opus 5.5
|
d881812500
|
[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
|
2026-09-24 14:14:10 +00:00 |
|
|
Linze Shi
|
484c211fe8
|
[Bugfix][Pooling] Fix JinaVL label configuration and restore multimodal tests (#57347)
Signed-off-by: Linze-Shi <linzeshi0@gmail.com>
|
2026-09-24 13:51:25 +00:00 |
|
|
Harry MellorandClaude Opus 5.5
|
cccf7e1376
|
Remove .gemini/ and CLAUDE.md (#58541)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
|
2026-09-24 12:57:23 +00:00 |
|
|
Fangzhou AiandClaude Opus 5.5
|
721d0e5c11
|
[ROCm][DSv4.1][Perf] Emit MXFP8 from the sparse decode reduce and run wo_a as a grouped FP8 GEMM (#58456)
Signed-off-by: fai <fangzhouai@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-09-24 11:58:14 +00:00 |
|