 Andreas KaratzasandGitHub
|
7b43db210c
|
[ROCm][CI][Bugfix] Multi-Modal Model Support Fixes and Attention Backend Improvements (#30270)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2025-12-19 02:17:27 +00:00 |
|
|
Isotr0pyandGitHub
|
700a5ad6c6
|
[MM Encoder]: Migrate legacy ViT MultiHeadAttention to new MMEncoderAttention interface (#30684)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-12-19 02:04:19 +08:00 |
|
|
|
28d15ab56b
|
adds jais 2 support (#30188)
Signed-off-by: sarathc-cerebras <sarath.chandran@cerebras.net>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
|
2025-12-18 15:46:58 +00:00 |
|
|
zzhxxxandGitHub
|
b166ef20e1
|
[refactor] Add prefix support to embed_tokens in DeepSeek MTP (#30788)
Signed-off-by: zzhx1 <zzh_201018@outlook.com>
|
2025-12-18 04:45:56 +00:00 |
|
|
Isotr0pyandGitHub
|
6fe5887652
|
[Chore] Remove v0 dead code for Qwen2.5-omni (#30883)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-12-17 19:54:39 -08:00 |
|
|
Isotr0pyandGitHub
|
74a1ac38b0
|
[v1] Add PrefixLM support to TritonAttention backend (#30386)
|
2025-12-17 16:05:24 -08:00 |
|
|
KimHyeminandGitHub
|
196cdc3224
|
[Model] Gemma3: Support untied word embeddings (#30827)
Signed-off-by: www-spam <panmahm@naver.com>
|
2025-12-17 07:11:18 -08:00 |
|
|
baoqian426andGitHub
|
84896fda22
|
[Bugfix] deepseek-V3.2 self.weights_proj has no bias (#30841)
Signed-off-by: baoqian <1354987947@qq.com>
Signed-off-by: baoqian426 <1354987947@qq.com>
|
2025-12-17 03:32:34 -08:00 |
|
|
Asaf Joseph GardinandGitHub
|
a9e15c21ef
|
[Mamba] Removed disable cascade attn in MambaModelConfig (#30712)
Signed-off-by: asafg <39553475+Josephasafg@users.noreply.github.com>
|
2025-12-17 08:48:53 +00:00 |
|
|
Grzegorz K. KarchandGitHub
|
f5db6385a1
|
Fix nemotron_nas intermediate_size computation (#30795)
Signed-off-by: Grzegorz Karch <gkarch@nvidia.com>
|
2025-12-17 01:06:28 +00:00 |
|
|
|
f5f51e5931
|
[Core][MM] Optimize encoder cache manager by operating with embeddings only (#30475)
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Sun Kim <sunytokki@gmail.com>
|
2025-12-16 14:18:17 -08:00 |
|
|
Harry MellorandGitHub
|
0b0acc758e
|
Remove head_mask from Ultravox and Swin (#30764)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-12-16 08:02:41 -08:00 |
|
|
Harry MellorandGitHub
|
6f15ac5de7
|
Don'e assume position_embedding_type will be present for BERT and RoBERTa models (#30770)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-12-16 13:40:26 +00:00 |
|
|
Isotr0pyandGitHub
|
e94384bbad
|
[Bugfix] Fix broken ViT attention selection for Blackwell device (#30731)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-12-16 05:24:32 +00:00 |
|
|
|
3bd9c49158
|
[CustomOp] Extract ApplyRotaryEmb as CustomOp and unify the dispatch logic (#29873)
Signed-off-by: shen-shanshan <467638484@qq.com>
Co-authored-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2025-12-15 19:08:16 -08:00 |
|
|
Max HuandGitHub
|
3f175f18a2
|
[Bugfix] Fix multimodal configuration for Qwen3VL MOE model (#30670)
Signed-off-by: Max Hu <hyoung2991@gmail.com>
|
2025-12-15 14:06:01 +00:00 |
|
|
|
e4806d973a
|
[BugFix] Add embed_input_ids method to make QWenLMHeadModel a vllm model (#30674)
Signed-off-by: root <iwzbi@zju.edu.cn>
Co-authored-by: root <iwzbi@zju.edu.cn>
|
2025-12-15 10:38:29 +00:00 |
|
|
wang.yuqiandGitHub
|
4429d934de
|
[Model] Automatic conversion of TokenClassification model (#30666)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
|
2025-12-15 08:13:00 +00:00 |
|
|
|
1adeb3b84c
|
[New Model] BAGEL support (AR only) (#28439)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2025-12-15 14:58:23 +08:00 |
|
|
|
87b4d1557d
|
[CustomOp][MM] Extract MMEncoderAttention as CustomOp and replace the backend of QwenVisionAttention with it. (#30125)
Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2025-12-15 11:13:32 +08:00 |
|
|
|
ae88aada38
|
[Feature]Add EVS (Efficient Video Sampling) Support for Qwen3-VL (#29752)
Signed-off-by: zitian.zhao <zitian.zhao@tencentmusic.com>
Co-authored-by: deitxfge <huhaibo1990@126.com>
|
2025-12-14 05:24:56 -08:00 |
|
|
zifeitongandGitHub
|
48b8456ff9
|
[Bugfix] Revert Qwen2-VL part of change in #28271 (#30542)
Signed-off-by: Zifei Tong <zifeitong@gmail.com>
|
2025-12-14 05:20:08 -08:00 |
|
|
Ilya MarkovandGitHub
|
3224ea9915
|
[torch.compile] Add encoder tag for compilation (#30489)
Signed-off-by: ilmarkov <markovilya197@gmail.com>
|
2025-12-14 18:15:11 +08:00 |
|
|
|
3a20450d31
|
Add AudioFlamingo3 model support (#30539)
Signed-off-by: Lasha <26011196+lashahub@users.noreply.github.com>
Signed-off-by: Lasha Koroshinadze <26011196+lashahub@users.noreply.github.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2025-12-14 02:14:55 -08:00 |
|
|
Chen ZhangandGitHub
|
ace34e3783
|
[Bugfix] Qwen3-next with --hf-overrides \{\"num_hidden_layers\":8\} (#30433)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
|
2025-12-13 22:12:45 +08:00 |
|
|
Cyrus LeungandGitHub
|
64251f48df
|
[Chore] Adjust tokenizer import to avoid circular imports (#30601)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-12-13 04:42:39 -08:00 |
|
|
|
4fa7ce46f3
|
[Feature] Add SM103 (Blackwell Ultra) Support to vLLM (#30484)
Signed-off-by: LopezCastroRoberto <robertol.c510@gmail.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
|
2025-12-12 19:34:23 -08:00 |
|
|
Lucas WilkinsonandGitHub
|
3e41992fec
|
[Attention] Use sparse prefill kernel for fp8 kv-cache in DeepSeek-v3.2 (#27532)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2025-12-12 05:57:47 -08:00 |
|
|
Jaehwang JungandGitHub
|
f90319d5d1
|
[Bugfix] Schedule failure due to wrong get_image_size_with_most_features (#29692)
|
2025-12-12 02:27:20 -08:00 |
|
|
|
9f2fc16a69
|
[Bugfix][Model] Fix Afmoe rope_parameters issue (#30505)
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-12-12 02:53:57 +00:00 |
|
|
Nicolò LucchesiandGitHub
|
0efd9f867c
|
[Core] Whisper Enable Encoder Batching (#29421)
Signed-off-by: NickLucche <nlucches@redhat.com>
|
2025-12-11 21:06:51 +00:00 |
|
|
Harry MellorandGitHub
|
cf3eacfe58
|
Standardise get_rope to use rope_parameters["partial_rotary_factor"], not rotary_dim (#30389)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-12-11 20:45:23 +00:00 |
|
|
Harry MellorandGitHub
|
8781cd6b88
|
Add Eagle and Eagle3 support to Transformers modeling backend (#30340)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-12-11 17:02:10 +00:00 |
|
|
Harry MellorandGitHub
|
93db3256a4
|
Give pooling examples better names (#30488)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-12-11 16:22:58 +00:00 |
|
|
Cyrus LeungandGitHub
|
3a3b06ee70
|
[Misc] Improve error message for is_multimodal (#30483)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-12-11 06:39:51 -08:00 |
|
|
Cyrus LeungandGitHub
|
13d63b65e0
|
[Deprecation] Remove missed fallback for embed_input_ids (#30469)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-12-11 10:06:36 +00:00 |
|
|
Cyrus LeungandGitHub
|
979f50efd0
|
[Deprecation] Remove fallbacks for embed_input_ids and embed_multimodal (#30458)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-12-11 06:58:23 +00:00 |
|
|
gh-wfandGitHub
|
36c9ce2554
|
Ensure minimum frames for GLM 4.6V compatibility (#30285)
Signed-off-by: Wayne Ferguson <wayneferguson@gmail.com>
|
2025-12-11 05:26:49 +00:00 |
|
|
AnkerandGitHub
|
e8e8cd73e5
|
[Bugfix] Fix HunyuanOCR cross-image contamination in batch processing (#30344)
Signed-off-by: Lennart Brog <lennart.borg@list-ag.de>
Signed-off-by: Anker <20343812+anker-c2@users.noreply.github.com>
|
2025-12-10 18:09:31 +00:00 |
|
|
|
d017bceb08
|
[BugFix] Fix minimax m2 model rotary_dim (#30384)
Signed-off-by: xuebi <xuebi@minimaxi.com>
Co-authored-by: xuebi <xuebi@minimaxi.com>
|
2025-12-10 04:58:50 -08:00 |
|
|
haoyangli-amdandGitHub
|
06462392e4
|
[bugfix][quantization] fix quark qwen3 kv_cache quantization (#30308)
Signed-off-by: Haoyang Li <lihaoyang0109@gmail.com>
|
2025-12-10 03:24:12 +00:00 |
|
|
Tsukasa OIandGitHub
|
73a484caa1
|
[Model][Quantization] Fix / Add GGUF support for Qwen2 MoE models (#30307)
Signed-off-by: Tsukasa OI <floss_llm@irq.a4lg.com>
|
2025-12-09 19:13:10 +00:00 |
|
|
|
9c32df6101
|
[Bugfix] Qwen 3 VL Embedding loading (#30303)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2025-12-09 08:04:02 +00:00 |
|
|
|
fcd5306f65
|
Add latent MoE support (#30203)
Signed-off-by: Shahar Mor <smor@nvidia.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
|
2025-12-08 17:35:01 +00:00 |
|
|
|
184076c3fe
|
[DeepSeek v3.2] Make top-k work for any logit values. (#27568)
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2025-12-08 06:55:58 -08:00 |
|
|
wang.yuqiandGitHub
|
9e77ffca3f
|
[Model][7/N] Improve all pooling task | Deprecation as_reward_model. Extract hidden states prefer using new multi-vector retrieval API (#26686)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
|
2025-12-08 08:10:09 +00:00 |
|
|
Dazhi JiangandGitHub
|
bcb6f5947f
|
[Perf] Remove sync point in vit torch sdpa attn backend (#30232)
Signed-off-by: Dazhi Jiang <dazhi_jiang@163.com>
|
2025-12-08 07:12:42 +00:00 |
|
|
Cyrus LeungandGitHub
|
e83b7e379c
|
Revert "[Renderer] Separate out RendererConfig from ModelConfig (#30145)" (#30199)
|
2025-12-07 00:00:22 -08:00 |
|
|
Cyrus LeungandGitHub
|
27f4c2fd46
|
[Renderer] Separate out RendererConfig from ModelConfig (#30145)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-12-06 23:15:42 -08:00 |
|
|
Cyrus LeungandGitHub
|
671427efbf
|
[Model] Move multimodal_cpu_fields definition to field config (#30181)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-12-06 13:40:02 +00:00 |
|