 Chaunceyandzjy0516
|
3df4ae153e
|
[Core][KDA] Generalize Mamba prefill checkpoint builder and exporter (#57783)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>
|
2026-09-21 04:46:11 +00:00 |
|
|
|
ff0c885494
|
[Bugfix] DiffusionGemma: fix multimodal support (#57589)
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>
|
2026-09-21 00:05:24 -04:00 |
|
|
Woosuk KwonandCodex
|
9b49f92344
|
[Perf][DSV4.1] Overlap mHC coefficients for small TP batches (#57603)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-20 17:33:17 -07:00 |
|
|
|
7d99c2c4fd
|
[Feature][Humming] Humming feature integration (#56685)
Signed-off-by: jinzhen.ljz <jinzhen.ljz@antgroup.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2026-09-20 08:11:01 -07:00 |
|
|
ZyannandAbatom
|
9b2f34cad4
|
[Feature] support bf16 MoE router and mxfp4 MoE for MiMo V2 (#57784)
Signed-off-by: Zyann7 <62597503+Zyann7@users.noreply.github.com>
Co-authored-by: Abatom <182586866+Abatom@users.noreply.github.com>
|
2026-09-20 13:25:56 +00:00 |
|
|
Chauncey
|
bf01fc4a31
|
[GLM-5.3-Flash] Route kpool indexer top-k through the shared SparseIndexerTopk dispatcher (#57546)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
|
2026-09-20 11:17:59 +00:00 |
|
|
mahird3
|
0748d3bd57
|
[Model][LoRA] Enable LoRA support for VoyageQwen3BidirectionalEmbedModel (#57708)
Signed-off-by: Mahir Dursunoglu <142054011+mahird3@users.noreply.github.com>
|
2026-09-20 09:50:00 +00:00 |
|
|
Misha GoinandErinYin
|
e5fce7b56b
|
[Core][Kernel] Share persistent workspaces for Marlin and Humming (#57421)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: ErinYin <liang.yin@daocloud.io>
|
2026-09-20 17:28:33 +08:00 |
|
|
Yan Ma
|
d05da62e9c
|
[XPU] fix incorrect gdn kernel log for XPU path (#54871)
Signed-off-by: Yan Ma <yan.ma@intel.com>
|
2026-09-20 14:00:31 +08:00 |
|
|
|
0c90804c0b
|
[Bugfix] DiffusionGemma: cast the self-conditioning soft embed to the buffer dtype (#57462)
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>
|
2026-09-20 04:58:02 +00:00 |
|
|
|
133b71e0be
|
[Bugfix] Take padded path for ragged decode batches in sparse_attn_indexer (#52500)
Signed-off-by: pavelzak <pavel.zakharov@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-09-19 20:14:29 +00:00 |
|
|
|
5302d1fe40
|
[Model Runner V2] Support custom logits processors (#56497)
Signed-off-by: David Cheung <d7cheung@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-09-19 17:46:49 +00:00 |
|
|
Cyrus Leung
|
751f6807d9
|
[Refactor] Use dynamic MM cache in processor (#57674)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2026-09-19 15:38:00 +00:00 |
|
|
Lio Einaudi
|
41c4a3ed4e
|
[Kernel][Perf] Add sm_120 (RTX PRO 6000 / RTX 50) tuned configs for batch-invariant persistent matmul (#57456)
Signed-off-by: LioEinaudi <zhao3024667639@gmail.com>
|
2026-09-19 09:30:55 -04:00 |
|
|
|
fbe8a157fb
|
[ROCm][Perf] Enable the AITER GDN decode fast path for flat qkvz layouts (#53623)
Signed-off-by: Mikko Tukiainen <Mikko.Tukiainen@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-09-19 06:05:04 -07:00 |
|
|
vllmellm
|
211e252d0b
|
[Bugfix][Model] Fix MiMo-V2.5 fused fp8 qkv_proj sharding (pre-shard count is num_key_value_heads; MTP path too) (#57508)
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
|
2026-09-19 06:05:00 -07:00 |
|
|
siyuandIsotr0py
|
4cc15f2121
|
[Quantization] Let ModelOpt MXFP8 layers load pre-processed weights Purpose (#57316)
Signed-off-by: liusy58 <mg21330037@smail.nju.edu.cn>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
|
2026-09-19 09:16:39 +00:00 |
|
|
Woosuk Kwon
|
38537331d3
|
[Bugfix][DSA] Avoid runtime JIT for offset candidate end buffers (#57667)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-09-19 00:27:11 -07:00 |
|
|
Jiang WuandJiang Wu
|
01c7bf8813
|
[Bugfix][Model] Fix Aria expert weight names and layout (#57487)
Signed-off-by: Jiang Wu <245355730+JiangLLM@users.noreply.github.com>
Co-authored-by: Jiang Wu <245355730+JiangLLM@users.noreply.github.com>
|
2026-09-18 21:06:30 -07:00 |
|
|
Andreas KaratzasandOpenAI Codex
|
2c3fb4c545
|
[CI][ROCm] Deprecate DinD for MI250 test groups (#56162)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-18 14:13:35 -07:00 |
|
|
Matt MastracciandClaude Fable 5.1
|
63d9ad0a3a
|
[Model] DiffusionGemma: honor logprob_token_ids on the converging step (#57417)
Signed-off-by: Matt Mastracci <matthew@mastracci.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-09-18 16:11:27 -04:00 |
|
|
Harry MellorandClaude Opus 5
|
8a5cf54387
|
[Multimodal] Type dummy options per modality (#57576)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-18 17:29:11 +01:00 |
|
|
Cyrus Leung
|
dbf4b89cf2
|
[Misc] Remove unnecessary Transformers version guards (#57556)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2026-09-18 15:01:35 +00:00 |
|
|
|
1cdf1689e5
|
[Quantization][XPU] Enable int8_w8a8 MoE on the Triton backend for XPU (#53162)
Signed-off-by: Artur Fierka <artur.fierka@intel.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-09-18 22:38:15 +08:00 |
|
|
Kevin Liandkevinli
|
911548247a
|
[Distributed][MoonEP] BF16 integration of MoonEP balanced EP backend (#52101)
Signed-off-by: kevinli <306243285+kaijunli-infr@users.noreply.github.com>
Co-authored-by: kevinli <306243285+kaijunli-infr@users.noreply.github.com>
|
2026-09-18 10:34:01 -04:00 |
|
|
Julien DebacheandHarry Mellor
|
2bdae2a5a8
|
[fix] Mistral-Large-3 accuracy regression on main (#57563)
Signed-off-by: jdebache <jdebache@nvidia.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-09-18 14:19:16 +00:00 |
|
|
|
44dd18fe0b
|
[Model][Gemma4] Load Weights with AutoWeightsLoader (#55911)
Signed-off-by: Josephasafg <ajgard7@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>
|
2026-09-18 12:07:30 +00:00 |
|
|
Taneem Ibrahim
|
2b8a5495a8
|
[Mypy] Fix mypy typing for N/O models (#54142)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-09-18 12:50:01 +01:00 |
|
|
Yuwen ZhouandLi, Jiang <jiang1.li@intel.com>
|
b346479065
|
[CPU] Add CPU FP8 W8A8 linear/MoE support (#49942)
Signed-off-by: yuwenzho <yuwen.zhou@intel.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
|
2026-09-18 17:59:42 +08:00 |
|
|
meng-amd
|
6df2b1a8c6
|
[Quantization] Support native Quark W4A16 INT4/UINT4 exports in vLLM (#48606)
Signed-off-by: HongWei Meng <HongWei.Meng@amd.com>
|
2026-09-18 17:52:46 +08:00 |
|
|
SunandCodex
|
42a33039eb
|
[Perf] Fuse CohereASR relative attention score accumulation (#55190)
Signed-off-by: levius <2114377220@qq.com>
Co-authored-by: Codex <codex@openai.com>
|
2026-09-18 06:18:41 +00:00 |
|
|
Woosuk KwonandCodex
|
64563d0ec4
|
[Bugfix][DSv4.1] Preserve NaN-scored candidate block indices (#57454)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-17 19:00:10 -07:00 |
|
|
Matt Mastracci
|
2c88fb131c
|
[Bugfix] DiffusionGemma: hand out stashed logprobs only on the committing step (#57414)
|
2026-09-17 20:24:58 -04:00 |
|
|
Rohan PotdarandClaude
|
213c379fca
|
[ROCm][Bugfix] Gate AITER MXFP8 MoE on the aiter enable flag (#57426)
Signed-off-by: Rohan Potdar <rohan.potdar@amd.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-09-18 00:06:05 +00:00 |
|
|
Yan Ma
|
48f663c37f
|
[XPU] Fix incorrect context-key normalization for Qwen DFlash-based models (#56431)
Signed-off-by: Yan Ma <yan.ma@intel.com>
|
2026-09-18 07:52:01 +08:00 |
|
|
Misha Goin
|
ac78445bc9
|
[MoE] Encapsulate TRT-LLM BF16 weight layout handling (#57405)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-09-17 17:47:30 -04:00 |
|
|
Misha Goin
|
db7a24c230
|
[Perf] Add fused DFlash2 grouped convolution (#55960)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-09-17 21:38:59 +00:00 |
|
|
rasmithandShanshan Shen
|
acc2ed2a5f
|
[ROCm][CI][The Rock 10] Fix (MI355) Quantized Models failure on The Rock 10 with Triton 3.8.x (#54849)
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
|
2026-09-17 15:20:35 -05:00 |
|
|
Doug Brown
|
2b02c6c29b
|
[Model] Add Cohere2MoE Eagle3 auxiliary hidden states (#49819)
Signed-off-by: Doug Brown <doug@github.douggo.com>
|
2026-09-17 20:09:36 +00:00 |
|
|
|
ac2f0ea82c
|
[MoE][Bugfix] Skip SP padded rows in grouped MoE routing (#56079)
Signed-off-by: Elvir Crncevic <elvircrn@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
|
2026-09-17 19:36:19 +00:00 |
|
|
MattandClaude Opus 5
|
fef55fd26d
|
[ROCm][CI] Adapt MoE tests to the triton_kernels 3.8 API (#57385)
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-17 11:21:22 -05:00 |
|
|
Taneem IbrahimandHarry Mellor
|
e960ead0aa
|
[Mypy] Fix mypy typing for Transformers models (#54320)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-09-17 12:11:31 -04:00 |
|
|
Zoe923
|
6a7de3ba3a
|
[Bugfix][GDN] Fix CuteDSL BF16 KKT inversion divergence (#53864)
Signed-off-by: Zoe923 <871844693@qq.com>
|
2026-09-17 08:49:56 -07:00 |
|
|
vllmellmandTJian
|
3affd35f31
|
[Fix][ROCm] MXFP4 MoE round-up inflates TP-sharded expert weights on CDNA3, starving KV cache (#56359)
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-09-17 22:52:12 +08:00 |
|
|
|
78fdf4efb8
|
[Bugfix][MoE] Convert FlashInfer BF16 weights in place (#54699)
Signed-off-by: Yuchen Wang <93700456+yuchenwang3@users.noreply.github.com>
Signed-off-by: Dakai An <dakaian108@gmail.com>
Co-authored-by: Dakai An <dakaian108@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
|
2026-09-17 22:00:04 +08:00 |
|
|
|
117cf43fb6
|
[HARDWARE][POWER] Enable W8A8 INT8 MoE on POWER (#55316)
Signed-off-by: Rukhaiya <bibirukhaiya123@gmail.com>
Signed-off-by: Akash kaothalkar <akash.kaothalkar@ibm.com>
Co-authored-by: Akash kaothalkar <akash.kaothalkar@ibm.com>
Co-authored-by: Antigravity <antigravity@google.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
|
2026-09-17 21:45:13 +08:00 |
|
|
Shantipriya Parida
|
0eae9acd4d
|
[Bugfix][ROCm][MoE] Fall back instead of crashing when AITER MoE is requested for a non-gated (is_act_and_mul=False) model (#56590)
Signed-off-by: Shantipriya Parida <shantipriya.parida@amd.com>
|
2026-09-17 13:39:26 +00:00 |
|
|
Lucas WilkinsonandRobert Shaw
|
fe284ea17d
|
[BugFxi] Fix DeepGEMM FP8 workspace over allocation (#53914)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-09-17 09:35:34 -04:00 |
|
|
|
08633cb5cd
|
[Qwen3.8-Flash-Next] Enable FP8 TP with FlashInfer TRTLLM MoE (#55867)
Signed-off-by: Canlin <canlinguosdu@gmail.com>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-09-17 08:56:28 +00:00 |
|
|
Jiahan Chang (Cyrus)andOpenAI Codex
|
4e5ffda19d
|
[Bugfix] Isolate supplemental FlashInfer BF16 autotuning (#57285)
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-17 07:38:58 +00:00 |
|