 Lukas GeigerandRoger Wang
|
07cadab27a
|
[Model][Qwen3VL] Cache positional embedding indices (#28475)
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2025-11-15 19:03:09 +00:00 |
|
|
Eldar Kurtić
|
e439c784fa
|
Add support for Eagle with separate lm-head and embed_tokens layers (#28549)
Signed-off-by: Eldar Kurtic <8884008+eldarkurtic@users.noreply.github.com>
|
2025-11-15 06:12:02 -08:00 |
|
|
|
085a525332
|
[Model] Fix lmhead init bug of bailing_moe (#28777)
Signed-off-by: hwhaokun <haokun0405@163.com>
Co-authored-by: zhaozx-cn <zhaozx2116@163.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-11-15 05:44:12 -08:00 |
|
|
tingtinggithub
|
cb15ee28db
|
Allow Gemma3 to take image embeddings (#28483)
Signed-off-by: tingtinggithub <streamttt@gmail.com>
|
2025-11-15 04:18:08 -08:00 |
|
|
Lukas GeigerandCyrus Leung
|
f05d474c8a
|
[Model][Qwen3VL] Use mm_position to compute mrope positions (#28730)
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2025-11-14 19:45:11 -08:00 |
|
|
GuanHandIsotr0py
|
cec275efce
|
[Bugfix] resolve Qwen3-VL GPTQModel quantized model loading failure (#28663)
Signed-off-by: GuanH <guansdrailib@gmail.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-11-14 18:44:27 +00:00 |
|
|
Fardin HoqueandWei Wei
|
964d65deed
|
LLaMA4 LoRA Adapter Enablement (#28602)
Signed-off-by: Fardin Hoque <kfhfar@amazon.com>
Co-authored-by: Wei Wei <wwei6@meta.com>
|
2025-11-14 13:27:56 -05:00 |
|
|
Harry Mellor
|
5f3cd7f7f2
|
[Docs] Update the name of Transformers backend -> Transformers modeling backend (#28725)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-11-14 16:34:14 +00:00 |
|
|
dongbo910220
|
c934caee88
|
[Fix] improve aspect ratio in dummy image generation and add common VLM tests for PaddleOCR-VL (#28711)
Signed-off-by: dongbo910220 <1275604947@qq.com>
|
2025-11-14 16:07:20 +00:00 |
|
|
zhaozx-cn
|
433c0f8675
|
[Model] Fix bailing_moe accuracy problem (#28277)
Signed-off-by: zhaozx-cn <zhaozx2116@163.com>
|
2025-11-14 13:33:02 +00:00 |
|
|
Shanshan ShenandIsotr0py
|
41b92f7d38
|
[Model][MM] Extract conv layer as CustomOp (#28455)
Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-11-14 19:16:13 +08:00 |
|
|
Jiangyun Zhu
|
c36bcfe6b3
|
[Bugfix] fix dots.ocr pp support (#28705)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
|
2025-11-14 09:01:26 +00:00 |
|
|
Yuanping Song
|
3035d1a166
|
[BugFix] DeepSeek-OCR: apply NoRepeatNGramLogitsProcessor to greedy path (#28617)
Signed-off-by: Yuanping Song <yuanping.song@outlook.com>
|
2025-11-13 15:24:35 +00:00 |
|
|
Harry Mellor
|
97d1c99302
|
Rename clashing method names for vLLM model protocol (#27583)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-11-12 19:14:33 -08:00 |
|
|
Harry Mellor
|
51c599f0ec
|
Skip models that cannot currently init on Transformers v5 (#28471)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-11-12 23:43:57 +00:00 |
|
|
Canlin Guo
|
bc5bd45c7d
|
[Refactor] Remove redundant TP gather/split in split_qkv in QwenVL (#28271)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
|
2025-11-12 15:56:47 +00:00 |
|
|
Jee Jee Li
|
a9d18b5107
|
[Bugfix] Fix gpt_oss packed_modules_mapping (#28536)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-11-12 21:02:06 +08:00 |
|
|
wuyaoxuehunandwuao.scotty
|
d3ade61e42
|
[Model] fix glm4_moe_mtp load weights with GLM-4.6 checkpoint. (#27597)
Signed-off-by: wuao.scotty <wuao.scotty@bytedance.com>
Co-authored-by: wuao.scotty <wuao.scotty@bytedance.com>
|
2025-11-12 10:14:00 +00:00 |
|
|
yyzxw
|
1761dea1a8
|
[BugFix]: --enable-lora with model granite-4.0-micro crash (#27733)
Signed-off-by: zxw <1020938856@qq.com>
|
2025-11-12 09:03:56 +00:00 |
|
|
Fanli Lin
|
b9ce9a3013
|
[BugFix] Add fallback path in apply_rotary_pos_emb_flashattn for non-cuda platforms (#28447)
Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
|
2025-11-12 03:13:21 +00:00 |
|
|
Lukas Geiger
|
cbb799e314
|
[Model][Qwen3VL] Simplify get_mrope_input_positions using numpy (#28302)
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
|
2025-11-12 02:55:10 +00:00 |
|
|
Jee Jee Li
|
9d1c474704
|
[LoRA][1/N]Remove LoRA extra vocab (#28382)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-11-11 11:06:21 -08:00 |
|
|
Fanli Lin
|
d5edcb8678
|
[BugFix] Fix Siglip2Attention on XPU (#28448)
Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
|
2025-11-11 18:18:02 +00:00 |
|
|
xuebwang-amd
|
5a1271d83a
|
[Quantization] fix attention quantization of gpt_oss model (#27334)
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
|
2025-11-11 12:06:00 -05:00 |
|
|
Fanli Lin
|
b886068056
|
[BugFix] Fix RuntimeError in PixtralHFAttention on CPU/XPU (#28444)
Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
|
2025-11-11 15:29:33 +00:00 |
|
|
Cyrus Leung
|
afffd3cc8a
|
[Model] Pass mm_features directly into get_mrope_input_positions (#28399)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-11-11 21:14:48 +08:00 |
|
|
Matthew BonanniandLuka Govedič
|
b30dfa03c5
|
[Attention] Refactor CUDA attention backend selection logic (#24794)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
|
2025-11-11 07:40:44 -05:00 |
|
|
Lukas Geiger
|
9973e6e04a
|
[Model][Qwen3VL] Slighly speedup fast_pos_embed_interpolate (#28434)
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
|
2025-11-11 10:35:10 +00:00 |
|
|
Fanli Lin
|
c7991269dd
|
[BugFix] 'DeepseekV2Config' object has no attribute 'use_mla'` (#28387)
Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
|
2025-11-11 08:45:38 +00:00 |
|
|
Jiangyun Zhu
|
f0359fffa4
|
[Bugfix] fix qwen3-next crash (#28202)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
|
2025-11-11 08:24:28 +00:00 |
|
|
Roger Wang
|
4fd4b743a2
|
[Bugfix] Fix max image size for PaddleOCR-VL (#28442)
Signed-off-by: Roger Wang <hey@rogerw.io>
|
2025-11-11 08:07:24 +00:00 |
|
|
jiahanc
|
34553b9d27
|
[Performance] Support FP8 flashinfer TRTLLM MOE on Qwen3 and Qwen-3next (#27492)
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
|
2025-11-10 12:34:57 -05:00 |
|
|
Cyrus Leung
|
d0e186c16f
|
[V0 Deprecation] Remove unused context_len and seq_len from M-RoPE (#28395)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-11-11 00:30:06 +08:00 |
|
|
vllmellmandLuka Govedič
|
f080a83511
|
[RFC][ROCm][AITER] Keep all AITER kernels in _aiter_ops class like _custom_ops and _ipex_ops (#24490)
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
|
2025-11-10 08:20:53 -08:00 |
|
|
Ferreboandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
912744d066
|
[Fix] optimize visual token mask with caching and multi-token support (#28374)
Signed-off-by: Ferrebo <itachi971009@gmail.com>
Signed-off-by: kebo01 <kebo01@baidu.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2025-11-10 13:23:49 +00:00 |
|
|
Yu Jiaqi
|
15be507c86
|
[bugfix] fix siglip batch text output error (#28365)
Signed-off-by: piood <2477084691@qq.com>
|
2025-11-10 21:21:15 +08:00 |
|
|
Jiangyun Zhu
|
c4768dcf47
|
[Kernel] Fix fused_gdn_gating (#28343)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
|
2025-11-09 14:26:35 -07:00 |
|
|
Jiangyun Zhu
|
7ae5a5fb11
|
[Misc] Add some comments in qwen3-next (#28267)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
|
2025-11-08 23:59:24 -08:00 |
|
|
Mohammad Miadh Angkad
|
404d7a9d14
|
[Performance][gpt-oss] Revert gpt-oss max cudagraph size to 1024 (#28345)
Signed-off-by: Mohammad Miadh Angkad <MAngkad.BSDSBA2027@aim.edu>
|
2025-11-08 15:50:10 -07:00 |
|
|
Isotr0pyandKunshang Ji
|
934a9c3b79
|
[Model] Consolidate Deepseek-MoE implementation with DeepSeek-v2 (#28101)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2025-11-08 05:01:27 +00:00 |
|
|
Lukas Geiger
|
e0919f331d
|
[Core][MM] Add mechanism to configure multimodal fields which should stay on CPU (#28168)
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
|
2025-11-07 12:14:29 +00:00 |
|
|
Kevin H. Luu
|
8e19d470af
|
[fix] Revert "fixing mm placeholder replacement issue with gemma3" (#28285)
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
|
2025-11-07 12:09:09 +00:00 |
|
|
Mengqing Cao
|
1958bda9b4
|
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
Signed-off-by: MengqingCao <cmq0113@163.com>
|
2025-11-07 19:38:38 +08:00 |
|
|
Harry Mellor
|
c0a4b95d64
|
Fix issues from #28242 (#28257)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-11-07 04:23:17 +00:00 |
|
|
Lucas Kabela
|
4bf56c79cc
|
[Multimodal][torch.compile] Add compilation config field for turning off ViT/MM compile (#28242)
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
|
2025-11-07 00:16:03 +00:00 |
|
|
Julien Denize
|
7a8375f8a0
|
Add llama 4 scaling support (#28145)
Signed-off-by: Julien Denize <julien.denize@mistral.ai>
|
2025-11-06 18:55:17 +00:00 |
|
|
|
201dc98acc
|
Fix hard-coded parameter name in gemma3n.py (#27946)
Signed-off-by: Seungduk Kim <seungduk.kim@yanolja.com>
Signed-off-by: Biswa Panda <biswa.panda@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Biswa Panda <biswa.panda@gmail.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
|
2025-11-05 23:07:36 -08:00 |
|
|
Isotr0py
|
43ecd0a900
|
[Chore] Clean up deepseek v2/v3 config copy (#28055)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-11-06 03:46:30 +00:00 |
|
|
Vadim Gimpelson
|
b6a248bdd7
|
[PERF] Decouple projections from GDN custom op. Attempt 2 (#28083)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
|
2025-11-05 17:01:12 -08:00 |
|
|
wang.yuqi
|
802748bddb
|
[Bugfix] Fix Qwen3-Reranker-8B load (#28117)
Signed-off-by: wang.yuqi <noooop@126.com>
|
2025-11-05 18:33:50 +00:00 |
|