 Benjamin Chislett
|
bf3ffb61e6
|
[Bugfix] Fix ChunkedLocalAttention CUDA Graph setting (#28739)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
|
2025-11-14 14:14:46 -08:00 |
|
|
|
15ae8e0784
|
[Bugfix][CI/Test][Spec Decode] Fix illegal memory access in offline_inference/spec_decode.py (Issue 27619) (#28432)
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2025-11-13 22:34:01 -08:00 |
|
|
Huamin Li
|
07a606aa7e
|
[CI Failure] Fix backend selection for encoder-only models (#28534)
Signed-off-by: Huamin Li <3ericli@gmail.com>
|
2025-11-13 10:11:27 -05:00 |
|
|
Benjamin Chislett
|
304419576a
|
[Perf] Refactor cudagraph_support to enable full CUDA graphs for spec decoding with FlashInfer (#28479)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
|
2025-11-13 01:56:40 +09:00 |
|
|
Nicolò LucchesiandMark McLoughlin
|
728a9eb70e
|
[Misc] Refactor Attention kv transfer methods into decorator (#27816)
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
|
2025-11-12 16:05:44 +00:00 |
|
|
wangxiyuan
|
10138c92a5
|
[V0 deprecation] Deprecate use_v1 parameter (#28112)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
|
2025-11-12 14:03:52 +00:00 |
|
|
Andreas Karatzas
|
9f0247cfa4
|
VLLM_USE_TRITON_FLASH_ATTN V0 variable deprecation (#27611)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
|
2025-11-11 18:34:36 -08:00 |
|
|
Li, Jiang
|
7f829be7d3
|
[CPU] Refactor CPU attention backend (#27954)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2025-11-12 09:43:06 +08:00 |
|
|
Lukas Geiger
|
76e4dcf225
|
[Misc] Remove unused attention prefix prefill ops functions (#26971)
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
|
2025-11-11 18:26:04 +00:00 |
|
|
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 |
|
|
|
cc079763c5
|
[BugFix] Avoid calling KV connector layer APIs when metadata is unset (#28253)
Signed-off-by: David Ben-David <davidb@pliops.com>
Co-authored-by: David Ben-David <davidb@pliops.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
|
2025-11-10 23:39:36 -08:00 |
|
|
Lucas Wilkinsonandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
39029d5192
|
[CI/Test Fix] Fix CP tests on Blackwell (#28404)
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>
|
2025-11-11 01:36:29 +00:00 |
|
|
Adrian Abeyta
|
a5a790eea6
|
[Bugfix] Ensure calculated KV scales are applied in attention. (#27232)
Signed-off-by: adabeyta <aabeyta@redhat.com>
|
2025-11-10 23:42:37 +00:00 |
|
|
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 |
|
|
Lucas Wilkinson
|
e8697faf03
|
[V0 deprecation] Remove no longer used get_metadata_cls (#28370)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2025-11-10 14:32:09 +08:00 |
|
|
zhangsicheng5andQiuChunshuo
|
2108a571d7
|
[DCP] Support dcp kv_cache interleave size > 1 (#26696)
Signed-off-by: zhangsicheng5 <zhangsicheng5@huawei.com>
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Signed-off-by: Qiu <qiuchunshuo@huawei.com>
Co-authored-by: QiuChunshuo <qiuchunshuo@huawei.com>
|
2025-11-09 04:45:27 +09:00 |
|
|
wangxiyuan
|
428bc7bf1c
|
[V0 deprecation] Remove VLLM_USE_V1 usage in most modules (#27955)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
|
2025-11-04 20:51:16 -08:00 |
|
|
Kunshang Ji
|
18b39828d9
|
[XPU] Add gpt-oss model support for Intel GPU (#27786)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
|
2025-11-05 02:17:23 +00:00 |
|
|
Lucas Kabela
|
55011aef24
|
[Bugfix][Qwen][Multimodal] Move Qwen2_5_vl sdpa to custom op and reenable compile (#27764)
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
|
2025-11-03 11:12:15 -08:00 |
|
|
|
7e2729b57e
|
[Multimodal][XPU]Enable vision attn backend for xpu platform (#27525)
Signed-off-by: Yan Ma <yan.ma@intel.com>
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Co-authored-by: Yejing Lai <yejing.lai@intel.com>
Co-authored-by: Guancheng Fu <110874468+gc-fu@users.noreply.github.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2025-11-01 04:45:02 +00:00 |
|
|
Lucas Kabela
|
94666612a9
|
[Misc][qwen2_5_vl][torch.compile] Enable supports_torch_compile on generic nn.Module and demonstrate speedup on Qwen Vision model (#23207)
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
Signed-off-by: Lucas Kabela <lucasakabela@gmail.com>
|
2025-10-28 22:36:43 +00:00 |
|
|
Yeshwanth N
|
71b1c8b667
|
[Chore]:Extract math and argparse utilities to separate modules (#27188)
Signed-off-by: Yeshwanth Surya <yeshsurya@gmail.com>
Signed-off-by: Yeshwanth N <yeshsurya@gmail.com>
Signed-off-by: yeshsurya <yeshsurya@gmail.com>
|
2025-10-26 04:03:32 -07:00 |
|
|
JartXandtjtanaa
|
65d2cf9511
|
[BUGFIX][ROCM] ViT FlashAttention on ROCm (no GFX9) and contiguous on qwen3vl ROCm TORCH_SDPA (#27190)
Signed-off-by: JartX <sagformas@epdcenter.es>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2025-10-26 15:08:52 +08:00 |
|
|
Matthew Bonanni
|
a99564ac5b
|
[Attention] Add missing kv cache scale setup (#27490)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
|
2025-10-25 00:12:49 -07:00 |
|
|
|
570c3e1cd4
|
[Bugfix] Honor --mm_encoder_attn_backend when used (#27124)
Co-authored-by: Bradley D <4551889+bradleyhd@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2025-10-23 20:09:52 +08:00 |
|
|
Tao HeandLucas Wilkinson
|
250fb1b8ea
|
[Bugfix] fixes the decoding metadata of dense mla's fp8 kvcache. (#27144)
Signed-off-by: Tao He <linzhu.ht@alibaba-inc.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2025-10-21 18:27:03 +00:00 |
|
|
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 |
|
|
Isotr0py
|
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 |
|
|
Nicolò Lucchesi
|
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 |
|
|
Zhuohan Li
|
d29483b58a
|
[Minor] Remove unnecessary error message (#27115)
Signed-off-by: Zhuohan Li <zhuohan123@gmail.com>
|
2025-10-17 20:02:12 +00:00 |
|
|
Cyrus Leung
|
4d4d6bad19
|
[Chore] Separate out vllm.utils.importlib (#27022)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-10-17 00:48:59 +00:00 |
|
|
rongfu.leng
|
5afd3276df
|
[Feature] Add process_weights_after_loading to AttentionImpl (#26870)
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
|
2025-10-16 08:02:30 -07:00 |
|
|
Adrian AbeytaandLuka Govedič
|
0a9ef0cfce
|
Move query quantization to attention layer for Flashinfer & Triton. (#26534)
Signed-off-by: adabeyta <aabeyta@redhat.com>
Signed-off-by: Adrian Abeyta <aabeyta@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
|
2025-10-15 19:01:38 -04:00 |
|
|
Mengqing Cao
|
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 |
|
|
Luka Govedič
|
2dcd12d357
|
[torch.compile] Fix tests for torch==2.9 inductor partition (#26116)
Signed-off-by: ProExpertProg <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
|
2025-10-14 19:55:02 -04:00 |
|
|
Boyuan Fengandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
a86b4c58e8
|
remove attn output view kernel (#26680)
Signed-off-by: Boyuan Feng <boyuan@meta.com>
Signed-off-by: Boyuan Feng <fby.1994@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2025-10-14 22:53:10 +00:00 |
|
|
Jaya Yuan
|
ea97940d6c
|
[DCP] Support Decode Context Parallel (DCP) for GQA with FlashAttention (#24864)
Signed-off-by: yuanyongjie.yyj <yuanyongjie.yyj@antgroup.com>
Signed-off-by: FENP <32334296+FENP@users.noreply.github.com>
Signed-off-by: Jaya Yuan <yuanyongjie.yyj@antgroup.com>
|
2025-10-14 13:07:50 +00:00 |
|
|
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 |
|
|
Huamin Li
|
0cd103e7cb
|
CP: make correct_attn_out robust to 4‑D views and fix Triton arg binding (#26509)
Signed-off-by: Huamin Li <3ericli@gmail.com>
|
2025-10-11 20:50:57 +00:00 |
|
|
Wenzheng Bi
|
ec10fd0abc
|
[Bugfix] Move current_platform import to avoid python import cache. (#16601)
Signed-off-by: iwzbi <wzbi@zju.edu.cn>
|
2025-10-09 10:46:19 +00:00 |
|
|
Zhiyuan Li
|
d24cf322e1
|
[Hybrid]: Decouple Kernel Block Size from KV Page Size (#24486)
Signed-off-by: lizhiyuan <uniartisan2017@gmail.com>
Signed-off-by: Zhiyuan Li <uniartisan2017@gmail.com>
|
2025-10-08 23:43:39 -07:00 |
|
|
Naveenraj KamalakannanandLuka Govedič
|
e614ab7806
|
Separate MLAAttention class from Attention (#25103)
Signed-off-by: Naveenraj Kamalakannan <therealnaveenkamal@gmail.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
|
2025-10-08 17:11:11 -07:00 |
|
|
Matthew Bonanni
|
2a03f93de9
|
[Attention] Register FLASHMLA_SPARSE (#26441)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
|
2025-10-08 22:28:52 +00:00 |
|
|
Matthew Bonanni
|
76879cc160
|
[Attention] Implement universal BACKEND_MAP (#25900)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
|
2025-10-08 12:00:25 -07:00 |
|
|
Lucas Wilkinson
|
f80e7866c0
|
[Misc] Clean up cruft from previous FlashMLA sparse implementation (#26125)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2025-10-08 10:09:34 +08:00 |
|
|
Gregory Shtrasberg
|
f231e5bc21
|
[ROCm] Split AITER unified attention into its own backend (#25507)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
|
2025-10-06 22:49:23 +00:00 |
|
|
Harry Mellor
|
6c04638214
|
Fix per file ruff ignores related to line length (#26262)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-10-06 05:12:40 +00:00 |
|
|
Harry Mellor
|
b893d661b1
|
Fix per file ruff ignores related to simplification (#26259)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-10-05 20:31:53 +00:00 |
|
|
Harry Mellor
|
1c0c68202c
|
Fix per file ruff ignores related to typing (#26254)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-10-05 16:37:55 +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 |
|