Cyrus Leung
cbd5e07a51
[Model] Use merge_by_field_config for MM models (Qwen series) ( #27546 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-27 05:38:05 +00:00
Cyrus Leung
66a168a197
[CI/Build] Refactor processing tests ( #27470 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-10-25 16:14:30 +00:00
Isotr0py
42efe609ba
[MM][Bugfix] Replace PatchEmbed's conv3d to linear layer ( #27418 )
...
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Roger Wang <hey@rogerw.io>
2025-10-24 07:32:47 +00:00
Cyrus Leung
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
Roger Wang
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
Cyrus Leung
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
燃
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
Jee Jee Li
9f4e30904b
[Model] Fix Qwen3VL mm mapping ( #27027 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-10-16 09:45:59 -07:00
Cyrus Leung
d2740fafbf
[Chore] Separate out vllm.utils.collections ( #26990 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-16 08:35:35 +00:00
Cyrus Leung
d2f816d6ff
[Bugfix] Standardize merging multimodal embeddings ( #26771 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-14 09:36:21 +00:00
Lukas Geiger
a6049be73c
[Models][Qwen3VL] Speedup fast_pos_embed_interpolate ( #26647 )
...
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
2025-10-13 01:20:07 +08:00
Harry Mellor
8fcaaf6a16
Update Optional[x] -> x | None and Union[x, y] to x | y ( #26633 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-10-12 09:51:31 -07:00
JJJYmmm
9d6cff3ede
[Bugfix][Qwen3VL] fix deepstack in qwen3vl ( #26626 )
...
Signed-off-by: liuye.hj <liuye.hj@alibaba-inc.com>
Signed-off-by: JJJYmmm <92386084+JJJYmmm@users.noreply.github.com>
Co-authored-by: liuye.hj <liuye.hj@alibaba-inc.com>
2025-10-11 05:58:33 -07:00
dsinghvi
727144bed1
[Refactor]: Use M-RoPE interface directly while defining model class instead of maintaining model specific M-RoPE implementation in mrope.py ( #24172 )
...
Signed-off-by: Divyansh Singhvi <divyanshsinghvi@gmail.com>
Signed-off-by: dsinghvi <divyanshsinghvi@gmail.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: wwl2755 <wangwenlong2755@gmail.com>
2025-10-11 07:21:04 +00:00
Lukas Geiger
b2155ed317
[Model][Qwen3VL] Compute cu_seqlens on CPU to remove ( #26496 )
...
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-10-10 09:42:17 -07:00
Lukas Geiger
2c1c7dfb35
[Models][Qwen] Replace pad with cat for better performance ( #26486 )
...
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
2025-10-09 14:51:26 +00:00
Lukas Geiger
0426e3c5e1
[Models][Qwen3VL] Optimise _validate_and_reshape_mm_tensor ( #26426 )
...
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
2025-10-09 10:25:48 +00:00
Lukas Geiger
93f2c0aa08
[Models] Improve iteration over layers ( #26425 )
...
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
2025-10-08 20:48:33 +00:00
Harry Mellor
d6953beb91
Convert formatting to use ruff instead of yapf + isort ( #26247 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-10-05 07:06:22 -07:00
Roger Wang
67bc0c003e
[Bugfix] Fix qwen3 vl dummy data generation with overrides ( #26193 )
...
Signed-off-by: Roger Wang <hey@rogerw.io>
2025-10-04 01:40:20 +00:00
Wenlong Wang
79aa244678
[Multi Modal] Configurable MM Profiling ( #25631 )
...
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-10-03 03:59:10 -07:00
TJian
9c5ee91b2a
[ROCm] [VL] [Bugfix] Fix vit flash attn dispatcher logic for ROCm ( #26104 )
...
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
2025-10-02 22:34:53 -07:00
Matthew Bonanni
2aaa423842
[Attention] Move Backend enum into registry ( #25893 )
...
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
2025-10-02 20:32:24 -07:00
Roger Wang
66bca9b8bd
[MM] Add text-only mode for Qwen3-VL ( #26000 )
2025-09-30 21:13:42 -07:00
Isotr0py
bd51f78e39
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge ( #25331 )
...
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: isotr0py <2037008807@qq.com>
2025-09-29 14:09:18 +08:00
Roger Wang
65ecb4f134
[Bugfix] Fallback ViT attn backend to SDPA for blackwell ( #25851 )
...
Signed-off-by: Roger Wang <hey@rogerw.io>
2025-09-29 06:03:51 +00:00
Isotr0py
0efd540dbc
[VLM] Update Qwen3-VL max_num_video_tokens calculation for configurable video profiling ( #25557 )
...
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>
2025-09-28 04:21:01 +00:00
Cyrus Leung
27d7638b94
[Bugfix] Merge MM embeddings by index instead of token IDs ( #16229 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
2025-09-27 08:15:12 +00:00
Wentao Ye
c242c98031
[Bugfix] Allow Only SDPA Backend for ViT on B200 for Qwen3-VL ( #25788 )
2025-09-26 20:44:52 -07:00
Isotr0py
d4d9899860
[Quantization] Add field to skip unquantized modules for GPTQ config ( #25455 )
...
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-09-26 15:47:41 +00:00
Isotr0py
17b4c6685c
[Bugfix] Fix Qwen3-VL max_num_video_tokens calculation for video profiling ( #25648 )
...
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-09-25 18:36:01 +08:00
Roger Wang
7be9ffcd9f
[Misc] Fix Qwen3-VL video_grid_thw typing ( #25646 )
...
Signed-off-by: Roger Wang <hey@rogerw.io>
2025-09-25 10:16:45 +00:00
Harry Mellor
8c853050e7
[Docs] Enable fail_on_warning for the docs build in CI ( #25580 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-09-24 19:30:33 +00:00
Cyrus Leung
babad6e5dd
[Misc] Move DP for ViT code inside model executor dir ( #25459 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-09-23 09:20:52 +00:00
Isotr0py
af7dfb0d1a
[Perf] Further optimization for Qwen3-VL fast_pos_embed_interpolate ( #25347 )
...
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-09-21 20:12:45 +00:00
Woosuk Kwon
1c3ffdbecc
[V0 Deprecation] Remove V0 sampling metadata ( #25345 )
...
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
2025-09-21 10:37:11 -07:00
Roger Wang
30d08911f7
[MM][Perf] Minor Optimization on Qwen3-VL fast_pos_embed_interpolate ( #25337 )
...
Signed-off-by: Roger Wang <hey@rogerw.io>
2025-09-21 11:05:20 +00:00
LJH-LBJ
d90e212a3a
Remove Redundant Assignment in Qwen3_VisionPatchMerger ( #25224 )
...
Signed-off-by: Junhong <liujunhong11@huawei.com>
Co-authored-by: Junhong <liujunhong11@huawei.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
2025-09-19 12:15:13 -06:00
Roger Wang
1dfea5f4a9
[Bugfix][Perf] Misc fixes for Qwen3 VL ( #25238 )
...
Signed-off-by: Roger Wang <hey@rogerw.io>
2025-09-19 10:46:16 +00:00
Roger Wang
3127274d02
[MM Encoder] Apply DP ViT for Qwen3-VL model series ( #24955 )
...
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Huang Jie <92386084+JJJYmmm@users.noreply.github.com>
Co-authored-by: 松灵 <26085463+wulipc@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-09-17 21:04:21 -07:00
Roger Wang
0f7acdd73c
[Model] Support Qwen3-VL Model Series ( #24727 )
...
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Huang Jie <92386084+JJJYmmm@users.noreply.github.com>
Co-authored-by: 松灵 <26085463+wulipc@users.noreply.github.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-09-17 05:01:04 +00:00
