e05a6754a8
[Model] Revert PR #26715 : Restore custom PaliGemma and Gemma3-MM impl… ( #27309 )
...
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com >
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com >
2025-10-22 10:05:34 -07:00
db6f28d898
[Bugfix] Fix HF format InternVL large variants video processing ( #27330 )
...
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn >
2025-10-22 08:39:23 -07:00
14e2f1231e
[Bugfix] Make get_mrope_input_positions instance methods ( #27342 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-10-22 08:38:34 -07:00
675aa2ec64
[Model] Upstream Deepseek-OCR model ( #27247 )
...
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn >
Signed-off-by: Roger Wang <hey@rogerw.io >
Co-authored-by: Roger Wang <hey@rogerw.io >
2025-10-22 07:59:15 -07:00
09a7e6f617
[Deepseek v3.2] Remove extra logics in indexer ( #26465 )
...
Signed-off-by: Siyuan Fu <siyuanf@nvidia.com >
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com >
Signed-off-by: Lain <siyuanf@nvidia.com >
Co-authored-by: Daniel Campora <961215+dcampora@users.noreply.github.com >
2025-10-21 23:34:03 +00:00
344a0017c0
[Performance] Dual stream execution of "shared_experts" and "selected_experts" inside FusedMoE ( #26440 )
...
Signed-off-by: Alexander Matveev <amatveev@redhat.com >
2025-10-21 21:38:29 +00:00
80e9452984
[Deepseek v3.2] Optimize top_k_per_row ( #26763 )
...
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com >
2025-10-21 08:30:07 +00:00
c3a2c6ac5f
[MM][Core] Decouple ViT backend from LM backend ( #27061 )
...
Signed-off-by: Roger Wang <hey@rogerw.io >
2025-10-21 00:30:10 -07:00
be4445072c
[Fix][Spec Decode] Fix llama4 draft loading with different quantization ( #27136 )
...
Signed-off-by: linzebing <linzebing1995@gmail.com >
2025-10-20 23:19:00 -07:00
f381cf2302
[Bugfix] Fix broken MTP weight loading for FP8 KV Scales ( #27227 )
...
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com >
2025-10-20 22:51:44 -07:00
aef368aa08
[BugFix] GPT-OSS Attention DP + MoE TP weight loading issue ( #24032 )
...
Signed-off-by: Po-Han Huang <pohanh@nvidia.com >
2025-10-21 04:03:47 +00:00
5f6cbf60d6
[Feature][Kernel]FusedMoE LoRA ( #21229 )
...
Signed-off-by: wuchen <cntryroa@gmail.com >
Signed-off-by: banjuede <lmklhc@163.com >
Signed-off-by: Chen Wu <cntryroa@gmail.com >
Signed-off-by: Danielle Robinson <dmmaddix@amazon.com >
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com >
Signed-off-by: bk-201 <joy25810@foxmail.com >
Co-authored-by: wuchen <wuchen@zetyun.com >
Co-authored-by: Nathan Van Gheem <vangheem@gmail.com >
Co-authored-by: banjuede <lmklhc@163.com >
Co-authored-by: Danielle Robinson <dmmaddix@amazon.com >
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com >
Co-authored-by: bk-201 <joy25810@foxmail.com >
2025-10-21 03:01:37 +00:00
352c0c8a28
[Quantization] Automatically infer AWQ modules_to_not_convert field ( #26909 )
...
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn >
2025-10-21 01:49:28 +00:00
e93ff6c8b9
Nemotron Nano V2 VL + EVS Video Support ( #27107 )
...
Signed-off-by: Eugene Khvedchenia <ekhvedchenia@nvidia.com >
Signed-off-by: Natan Bagrov <nbagrov@nvidia.com >
Signed-off-by: Roger Wang <hey@rogerw.io >
Co-authored-by: Natan Bagrov <nbagrov@nvidia.com >
Co-authored-by: Roger Wang <hey@rogerw.io >
2025-10-20 22:19:11 +08:00
f32bf7582e
[Model][VLM] Support Bee-8B Model ( #27012 )
...
Signed-off-by: uyzhang <yi.zhang.4096@gmail.com >
Signed-off-by: Yi Zhang <zhangyi970819@gmail.com >
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.io >
2025-10-20 02:31:26 +00:00
d31f7844f8
[Misc] Move utils to avoid conflicts with stdlib, and move tests ( #27169 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-10-19 05:20:55 -07:00
c2bba69065
[BugFix] Disable fp8 kv-cache by default for DeepSeek V3.2 ( #27121 )
...
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com >
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com >
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-10-18 22:05:23 +00:00
6ac5e06f7c
[Chore] Clean up pytorch helper functions in vllm.utils ( #26908 )
...
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn >
Signed-off-by: isotr0py <2037008807@qq.com >
2025-10-18 09:48:22 -07:00
5c2acb270a
[Models][QwenVL] Remove unnecessary .contiguous() calls ( #27106 )
...
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com >
2025-10-18 07:05:05 -07:00
b26b70bec4
[Misc] Refactor get_kv_cache_spec into AttentionLayerBase ( #26587 )
...
Signed-off-by: NickLucche <nlucches@redhat.com >
2025-10-18 13:51:21 +00:00
4c91a28e30
[bugfix] Qwen3-VL fix video incorrect timestamp calculations while do_sample_frames=True ( #27104 )
...
Co-authored-by: 松灵 <wpf272043@alibaba-inc.com >
2025-10-17 16:26:33 +00:00
daec4d2624
[Model]Improve Qwen3VLMoeForConditionalGeneration packed_modules_mapping ( #27096 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com >
2025-10-17 04:47:00 -07:00
6c9fdbf725
[Docs] Replace rst style double-backtick with md single-backtick ( #27091 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2025-10-17 02:47:34 -07:00
3aeb19a39e
[Model] Add support for LightOnOCR ( #26916 )
...
Signed-off-by: Said Taghadouini <taghadouinisaid@gmail.com >
Signed-off-by: Said Taghadouini <84044788+staghado@users.noreply.github.com >
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com >
2025-10-17 05:05:24 +00:00
8c017b3490
[Model] Always use Transformers backend for PaliGemma and Gemma3-MM ( #26715 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-10-17 05:03:35 +00:00
bde9e2272a
[Bugfix][Qwen] fixes the weights dtype in qwen3_next: it is actually a bfloat16 ( #27030 )
...
Signed-off-by: Tao He <linzhu.ht@alibaba-inc.com >
2025-10-17 03:37:52 +00:00
4d055ef465
Remove unused imports ( #26972 )
...
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com >
2025-10-16 19:51:17 -07:00
fb5e10d3fb
Refactor Transformers backend to use mixins ( #26906 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2025-10-16 21:50:39 +00:00
7bb736d00e
Fix Qwen2.5 VL image grid docstring ( #27033 )
...
Signed-off-by: zitian zhao <zitian.zhao@tencentmusic.com >
2025-10-16 09:57:36 -07:00
9f4e30904b
[Model] Fix Qwen3VL mm mapping ( #27027 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com >
2025-10-16 09:45:59 -07:00
dcbb3f1871
[Bugfix] Correct LayerNorm epsilon parameter in modernbert.py ( #27008 )
...
Signed-off-by: bogdanm <152898065+bogdan01m@users.noreply.github.com >
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-10-16 12:27:44 +00:00
e51928793e
[Model][Bugfix] fix ernie45 vl run failed from shared experts optimization ( #26885 )
...
Signed-off-by: wangyafeng <wangyafeng@baidu.com >
2025-10-16 03:37:35 -07:00
d2740fafbf
[Chore] Separate out vllm.utils.collections ( #26990 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-10-16 08:35:35 +00:00
7d8975de84
Deepseek-v3 Batch Invariant on 8xH100 ( #26609 )
...
Signed-off-by: Bram Wasti <bwasti@meta.com >
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com >
2025-10-15 22:06:02 -07:00
785d8b6410
[PERF] Qwen3-next MTP speedup (change bool mask indexing to index_select / index_copy to reduce d2h) ( #26437 )
...
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com >
2025-10-16 12:18:31 +08:00
f6cdc9a02f
[Chore] Rename utils submodules ( #26920 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-10-16 03:58:13 +00:00
1317034379
[ROCm][FEAT] Fuse DeepSeek shared experts into AITER fused_moe ops ( #24097 )
...
Signed-off-by: chenjun <junchen2@amd.com >
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com >
Co-authored-by: valarLip <103567126+valarLip@users.noreply.github.com >
Co-authored-by: TJian <tunjian.tan@embeddedllm.com >
2025-10-16 10:41:34 +08:00
d3cbaa08dc
Lower sevarity of log when model info cache misses due to exception ( #26917 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2025-10-15 09:01:09 -07:00
136a17fe6e
[Chore] Separate out vllm.utils.func ( #26904 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-10-15 13:03:58 +00:00
8f4b313c37
[Misc] rename torch_dtype to dtype ( #26695 )
...
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com >
2025-10-15 12:11:48 +00:00
f93e348010
[Misc] Remove isort and yapf ignores ( #26888 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-10-15 12:09:03 +00:00
f54f85129e
[Model][2/N] Improve all pooling task | Support multi-vector retrieval ( #25370 )
...
Signed-off-by: wang.yuqi <noooop@126.com >
2025-10-15 11:14:41 +00:00
5c3bae1a6a
[Fix] Remove divisibility requirement between num_kv_heads and tp_size in bailing_moe ( #26876 )
...
Signed-off-by: vito.yy <vito.yy@antgroup.com >
2025-10-15 16:44:04 +08:00
f5ed68ef63
[Deepseek-V3.2][Kernel] Integrate cuda indexer k cache gather ( #26456 )
...
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com >
2025-10-15 16:05:01 +08:00
302ef403a2
[DSA][MLA] Tiny refactor on DeepSeek to make it reusable for different backends ( #26656 )
...
Signed-off-by: MengqingCao <cmq0113@163.com >
2025-10-15 00:16:44 -07:00
8865da157b
[Bugfix][Multi Modal] Fix incorrect Molmo token processing ( #26873 )
...
Signed-off-by: sanghol <sanghol@allenai.org >
2025-10-15 07:13:59 +00:00
8c851f6d04
[Bugfix] Fix qwen3-omni audio truncation issue ( #26815 )
...
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn >
2025-10-15 05:38:36 +00:00
e9f1b8c9e9
Adjusted the model order of the model registration file ( #26798 )
...
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com >
2025-10-14 13:26:11 +00:00
9c4cb68339
[Chore] Remove SupportsV0Only interface and update supported models docs ( #26783 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-10-14 04:55:10 -07:00
74704d4553
[Model] Use merge_by_field_config for MM models (O-P) ( #26776 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-10-14 09:42:45 +00:00
