biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
8,240 Commits 2 Branches 140 Tags
f5d0f4784fdd93f1032f3bb81220af10d7588f5a
Commit Graph

171 Commits

Author SHA1 Message Date
Sage Moore
0edaf752d7 [Attention][DBO] Add support for "splitting" the CommonAttentionMetadata (#21153) 
Signed-off-by: Sage Moore <sage@neuralmagic.com>
 2025-08-01 19:47:53 -07:00
fhl2000
23322431c8 [V1][CUDA] Full cudagraph support for FlashInfer (#21367) 2025-08-01 21:49:34 -04:00
Michael Goin
f81c1bb055 [Bugfix] Check NVIDIA artifactory is accessible before using flashinfer cubin kernels (#21893) 2025-08-01 08:28:45 -04:00
Mickaël Seznec
e1a7fe4af5 [BugFix] fix: aot passes kvcache dtype information (#19750) 
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
 2025-08-01 05:45:02 +00:00
Michael Goin
61445453df [UX] Rename CUTLASS_MLA_VLLM_V1 to CUTLASS_MLA (#21966) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-07-30 20:40:34 -07:00
Yong Hoon Shin
ad510309ee Override attention metadata for fast prefill in some KV sharing setups (#21590) 
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
 2025-07-30 08:54:15 -07:00
Chen Zhang
555e7225bc [v1][attention] Support Hybrid Allocator + FlashInfer (#21412) 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
 2025-07-30 01:45:29 +00:00
elvischenv
58b11b24a6 [Bugfix] Fix workspace buffer None issue for Flashinfer TRTLLM Backend (#21525) 
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
 2025-07-29 10:34:00 -04:00
Asaf Joseph Gardin
a6c050286a [v1][mamba] Added mamba_type into MambaSpec (#21715) 
Signed-off-by: asafg <asafg@ai21.com>
Co-authored-by: asafg <asafg@ai21.com>
 2025-07-28 08:15:55 +00:00
Maximilien de Bayser
1cd6eaba54 Support encoder-only models without KV-Cache (#21270) 
Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
 2025-07-26 21:09:52 +08:00
who who who
b3caeb82e7 [ROCm][AITER] Enable fp8 kv cache on rocm aiter backend. (#20295) 
Signed-off-by: fsx950223 <fsx950223@outlook.com>
Signed-off-by: amd-ruitang3 <Rui.Tang2@amd.com>
Co-authored-by: amd-ruitang3 <Rui.Tang2@amd.com>
 2025-07-25 06:50:21 -07:00
weiliang
2dd72d23d9 update flashinfer to v0.2.9rc1 (#21485) 
Signed-off-by: Weiliang Liu <weiliangl@nvidia.com>
 2025-07-24 14:06:11 -07:00
Lucas Wilkinson
61b8cea3b4 [Attention] Optimize FlashInfer MetadataBuilder Build call (#21137) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-07-24 03:21:46 -07:00
Lucas Wilkinson
304dce7ec0 [Attention] Clean up iRoPE in V1 (#21188) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2025-07-21 09:10:30 -07:00
Chengji Yao
3a1d8940ae [TPU] support fp8 kv cache quantization (#19292) 
Signed-off-by: Chengji Yao <chengjiyao@google.com>
 2025-07-20 03:01:00 +00:00
Woosuk Kwon
752c6ade2e [V0 Deprecation] Deprecate BlockSparse Attention & Phi3-Small (#21217) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-07-19 13:53:17 -07:00
Lucas Wilkinson
59f935300c [BugFix] Fix potential cuda-graph IMA (#21196) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-07-19 02:18:47 -07:00
Lucia Fang
9a9fda1423 [Core] Support Local Chunked Attention for Hybrid KV Cache (#19351) 
Signed-off-by: Lucia Fang <fanglu@fb.com>
Signed-off-by: Lu Fang <fanglu@meta.com>
Signed-off-by: Lu Fang <fanglu@fb.com>
Co-authored-by: Lu Fang <fanglu@meta.com>
 2025-07-18 20:48:38 -07:00
Lucas Wilkinson
89cab4d01f [Attention] Make local attention backend agnostic (#21093) 2025-07-18 00:10:42 -04:00
elvischenv
8dfb45ca33 [Bugfix] Fix the tensor non-contiguous issue for Flashinfer TRT-LLM backend attention kernel (#21133) 2025-07-18 00:35:58 +00:00
Lucas Wilkinson
76b494444f [Attention] Refactor attention metadata builder interface (#20466) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-07-17 04:44:25 +00:00
QiliangCui
72ad273582 Remove torch_xla.tpu.version() from pallas.py. (#21065) 
Signed-off-by: Qiliang Cui <derrhein@gmail.com>
 2025-07-17 00:25:26 +00:00
Chengji Yao
85431bd9ad [TPU] fix kv_cache_update kernel block size choosing logic (#21007) 
Signed-off-by: Chengji Yao <chengjiyao@google.com>
 2025-07-16 04:39:48 +00:00
Peter Pan
1eb2b9c102 [CI] update typos config for CI pre-commit and fix some spells (#20919) 
Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>
 2025-07-15 21:12:40 -07:00
Elfie Guo
30800b01c2 [Nvidia] Integrate SM100 cudnn prefill API to MLA prefill (#20411) 
Signed-off-by: Elfie Guo <elfieg@nvidia.com>
Co-authored-by: Elfie Guo <eflieg@nvidia.com>
 2025-07-15 17:56:45 -07:00
Yifei Teng
c586b55667 [TPU] Optimize kv cache update kernel (#20415) 
Signed-off-by: Yifei Teng <tengyifei88@gmail.com>
 2025-07-15 03:56:43 -07:00
Alexander Matveev
8cdc371217 SM100 Cutlass MLA decode with unrestricted num_heads (< 128) for DeepSeek TP (#20769) 
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
 2025-07-15 01:06:38 +00:00
Cyrus Leung
e8cc53af5e [Misc] Log the reason for falling back to FlexAttention (#20699) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-07-14 04:16:51 -07:00
Pavani Majety
7bd4c37ae7 [Core] Add Flashinfer TRTLLM Backend for Flashinfer decode path (SM100). (#19825) 
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: shuw <shuw@nvidia.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-07-11 09:23:23 +00:00
nopperl
5d09152ff1 [V1] Enable Mamba2 layers other than MambaMixer2 in the v1 engine (#20660) 
Signed-off-by: nopperl <54780682+nopperl@users.noreply.github.com>
 2025-07-11 05:53:31 +00:00
Alexander Matveev
5b032352cc [Attention] MLA - Flashinfer Ragged Prefill (#20034) 2025-07-10 20:17:47 -07:00
Tuan, Hoang-Trong
47043eb678 [Kernel] Triton implementation of causal-conv1d for Mamba-based models (#18218) 
Signed-off-by: Tuan M. Hoang-Trong <tmhoangt@us.ibm.com>
Co-authored-by: Tuan M. Hoang-Trong <tmhoangt@us.ibm.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2025-07-09 12:53:55 -07:00
Akash kaothalkar
6db31e7a27 [Hardware][PPC64LE] Enable V1 for ppc64le and ARM (#20554) 
Signed-off-by: Akash Kaothalkar <akash.kaothalkar@ibm.com>
Co-authored-by: Akash Kaothalkar <akash.kaothalkar@ibm.com>
Co-authored-by: Nikhil Gupta <nikhil.gupta2@arm.com>
 2025-07-08 20:00:41 -07:00
Chenyaaang
e34d130c16 [TPU] Temporary fix vmem oom for long model len by reducing page size (#20278) 
Signed-off-by: Chenyaaang <chenyangli@google.com>
 2025-07-08 05:16:16 +00:00
Li, Jiang
7721ef1786 [CI/Build][CPU] Fix CPU CI and remove all CPU V0 files (#20560) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
 2025-07-07 22:13:44 -07:00
Cyrus Leung
9fb52e523a [V1] Support any head size for FlexAttention backend (#20467) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-07-06 09:54:36 -07:00
Isotr0py
32c9be2200 [v1] Re-add fp32 support to v1 engine through FlexAttention (#19754) 
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-07-05 09:41:10 +00:00
Jee Jee Li
1caca5a589 [Misc] Add SPDX-FileCopyrightText (#20428) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-07-04 07:40:42 +00:00
Nicolò Lucchesi
8d775dd30a [Misc] Fix Unable to detect current VLLM config. Defaulting to NHD kv cache layout warning (#20400) 
Signed-off-by: NickLucche <nlucches@redhat.com>
 2025-07-03 14:56:09 -07:00
vllmellm
a1aafc827a [ROCm][FEAT] Enable Full Graph Mode in AITER MLA V1 Attn Backend (Decode Phase only) (#20254) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-07-02 16:25:46 +00:00
Chengji Yao
7da296be04 [TPU] kv cache update kernel supports dynamic grid (#20235) 
Signed-off-by: Chengji Yao <chengjiyao@google.com>
 2025-07-02 06:33:37 +00:00
Liangliang Ma
a0389e0554 [UT][intel GPU] use current_platform instead of device hardcode in v1 tests (#20169) 
Signed-off-by: Ma, Liangliang <liangliang.ma@intel.com>
 2025-07-02 09:06:04 +08:00
Woosuk Kwon
8acb4badee [CUDA graphs] Enable full cuda graphs with FA3 AoT scheduling (#20301) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-07-01 09:07:36 -07:00
TY-AMD
96453cfa83 [BugFix][V1][ROCm] Triton MLA uses V0 backend on V1 engine (#19067) 
Signed-off-by: Tianyuan Wu <Tianyuan.Wu@amd.com>
 2025-07-01 16:12:19 +08:00
Chendi.Xue
dec197e3e5 Quick Fix by adding conditional import for flash_attn_varlen_func in flash_attn (#20143) 
Signed-off-by: Chendi.Xue <chendi.xue@intel.com>
 2025-06-27 05:48:13 +00:00
Chengji Yao
04e1642e32 [TPU] add kv cache update kernel (#19928) 
Signed-off-by: Chengji Yao <chengjiyao@google.com>
 2025-06-26 10:01:37 -07:00
Kunshang Ji
b69781f107 [Hardware][Intel GPU] Add v1 Intel GPU support with Flash attention backend. (#19560) 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
 2025-06-26 09:27:18 -07:00
TJian
27c065df50 [Bugfix][V1][ROCm] Fix AITER Flash Attention Backend (Fix API Break and Local Attention Logic: affecting Llama4) (#19904) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-06-26 12:42:31 +00:00
Chenyaaang
2d7620c3eb [TPU] Add TPU specific var VLLM_TPU_MOST_MODEL_LEN (#19919) 
Signed-off-by: Chenyaaang <chenyangli@google.com>
 2025-06-25 15:51:02 -07:00
Chengji Yao
2cc2069970 [TPU][Bugfix] fix kv cache padding (#20048) 
Signed-off-by: Chengji Yao <chengjiyao@google.com>
 2025-06-25 21:24:10 +00:00