iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
8,621 Commits 3 Branches 0 Tags
070da660c1bf9e7a7be8b9efeff4b06f91c7342f
Commit Graph
108 Commits
Author SHA1 Message Date
fhl2000Luka GovedičLucas WilkinsonLucas Wilkinson
 		74f441f4b5 [Core] Allow full cudagraph with separate attention routines and orthogonal to compilation, add support for FA2 and FlashInfer (#20059) 
Signed-off-by: fhl <2410591650@qq.com>
Signed-off-by: fhl2000 <63384265+fhl2000@users.noreply.github.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
 2025-08-15 10:01:39 -04:00
Yongye ZhuandMichael Goin 39cd09dc86 [Bugfix] use flash attn on sm90 (#22933) 
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2025-08-14 16:37:22 -07:00
Michael Goin b1361c7273 [Bugfix] Fix default enable for CUTLASS MLA on SM100 (#22738) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-08-12 21:22:05 -07:00
Woosuk Kwon 71683ca6f6 [V0 Deprecation] Remove multi-step scheduling (#22138) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
 2025-08-12 20:18:39 -07:00
Yongye Zhu 007dd90859 [gpt-oss] Enable gpt-oss on ampere (#22714) 
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
 2025-08-12 03:21:44 -07:00
Giancarlo Delfin 469b3ffaaa [V1] port xformers backend to v1 (#21342) 
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
 2025-08-05 10:04:46 -07:00
Giancarlo Delfin aa7012eb6d Add tree attention backend for v1 (part 1) (#20401) 
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
 2025-08-03 22:13:26 -07:00
vllmellmandtjtanaavllm d3a6f2120b [FEAT][ROCm] Enable running Flash Attention as ViT attn backend for Qwen-VL models on ROCm platform. (#22069) 
Signed-off-by: tjtanaavllm <tunjian.tan@amd.com>
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: tjtanaavllm <tunjian.tan@amd.com>
 2025-08-01 23:53:18 -07:00
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
Alexander Matveevandmgoin 8f605ee309 [Attention] Make CutlassMLA the default backend for SM100 (blackwell) (#21626) 
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-07-27 20:13:00 +00:00
elvischenv 2dec7c1a5d [Bugfix][CUDA] fixes CUDA FP8 kv cache dtype supported (#21420) 
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
 2025-07-22 20:34:50 -07:00
Varun Sundar RabindranathandVarun Sundar Rabindranath 8425f785ad [Misc] DeepEPHighThroughtput - Enable Inductor pass (#21311) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-07-21 23:35:45 -07:00
Konrad ZaworaandChendi.Xue c17231e827 Fix kv_cache_dtype handling for out-of-tree HPU plugin (#21302) 
Signed-off-by: Konrad Zawora <kzawora@habana.ai>
Signed-off-by: Chendi.Xue <chendi.xue@intel.com>
Co-authored-by: Chendi.Xue <chendi.xue@intel.com>
 2025-07-21 23:35:14 -07:00
Woosuk Kwon dd572c0ab3 [V0 Deprecation] Remove V0 Spec Decode workers (#21152) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-07-18 21:47:50 -07:00
Woosuk Kwon 54cf1cae62 [Misc] Do not print async output warning for v1 (#21151) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-07-17 21:57:02 -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
Congcong Chen 2c11a738b3 [Model] New model support for microsoft/Phi-4-mini-flash-reasoning (#20702) 
Signed-off-by: Congcong Chen <congcongchen@microsoft.com>
 2025-07-12 06:02:10 -07:00
Pavani Majetyshuwmgoin
 		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
Nick Hill ffbcc9e757 [BugFix] Fix VllmConfig() construction on all platforms (#20695) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-07-10 07:00:20 +00:00
Kunshang Ji 0b407479ef [misc]refactor Platform.set_device method (#20262) 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
 2025-07-09 01:39:47 +00:00
Yang YangandKunshang Ji 6e2c19ce22 [Refactor]Abstract Platform Interface for Distributed Backend and Add xccl Support for Intel XPU (#19410) 
Signed-off-by: dbyoung18 <yang5.yang@intel.com>
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
 2025-07-07 04:32:32 +00:00
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
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
kourosh hakhamaneshi 5e666f72cd [Bugfix][Ray] Set the cuda context eagerly in the ray worker (#19583) 2025-06-19 22:01:16 -07:00
Michael Goin 36239f79dd Fix FA2 fallback for Blackwell V1 (#19781) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-06-19 09:53:55 +08:00
Michael Goin af09b3f0a0 [Bugfix][V1] Allow manual FlashAttention for Blackwell (#19492) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-06-12 10:40:24 +00:00
Michael Goin 7484e1fce2 Add cache to cuda get_device_capability (#19436) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-06-11 17:37:05 +08:00
Isotr0py 5f1ac1e1d1 Revert "[v1] Add fp32 support to v1 engine through flex attn" (#19404) 2025-06-10 01:30:20 -07:00
Isotr0py b8089195b4 [v1] Add fp32 support to v1 engine through flex attn (#19319) 
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-06-09 22:10:44 +08:00
Driss Guessous cf02f9b283 Add FlexAttention to V1 (#16078) 
Signed-off-by: drisspg <drisspguessous@gmail.com>
 2025-06-06 21:58:55 -07:00
Benjamin Chislett 3465b87ef8 [Bugfix] Fix EAGLE vocab embedding construction for Llama 70B (#19033) 
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
 2025-06-05 19:10:08 -07:00
Michael Goin 87360308b7 [V1] Use FlashInfer by default on Blackwell GPUs (#19118) 2025-06-05 15:40:39 -04:00
Kaixi Hou 41aa578428 [NVIDIA] Add Cutlass MLA backend (#17625) 2025-06-03 21:40:26 -07:00
Varun Sundar RabindranathandVarun Sundar Rabindranath fa98d77773 [Kernel] DeepEP dispatch-combine kernel integration (#18434) 
Signed-off-by: Varun <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-06-03 12:30:02 -07:00
Simon Mo 02f0c7b220 [Misc] Add SPDX-FileCopyrightText (#19100) 
Signed-off-by: simon-mo <simon.mo@hey.com>
 2025-06-03 11:20:17 -07:00
Varun Sundar RabindranathandVarun Sundar Rabindranath 7951d78738 [Core] Enable CUDA graphs for DP + All2All kernels (#18724) 
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
 2025-05-28 22:55:30 +00:00
Mengqing Cao d781930f90 [Platform][Dist] Make torch distributed process group extendable (#18763) 
Signed-off-by: Mengqing Cao <cmq0113@163.com>
 2025-05-28 10:52:34 +00:00
youkaichao 6a7988c55b Refactor pplx init logic to make it modular (prepare for deepep) (#18200) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-05-23 23:43:43 +08:00
Mengqing Caoandyoukaichao f8d2cc5f55 [Compile][Platform] Make PiecewiseBackend pluggable and extendable (#18076) 
Signed-off-by: Mengqing Cao <cmq0113@163.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
 2025-05-22 12:11:53 -07:00
bnellnm f9c069c85e Modularize fused experts and integrate PPLX kernels (#15956) 2025-05-14 13:11:54 -07:00
Harry Mellor c8ea982d9b Update deprecated type hinting in platform, plugins, triton_utils, vllm_flash_attn (#18129) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-05-14 05:28:16 -07:00
Tao He 60f7624334 Implements dual-chunk-flash-attn backend for dual chunk attention with sparse attention support (#11844) 2025-05-12 19:52:47 -07:00
Jade Zheng 289199feb6 [Core] Use platform-agnostic device control for DP engine core (#17245) 
Signed-off-by: Jade Zheng <zheng.shoujian@outlook.com>
 2025-05-12 12:09:16 -07:00
Isotr0py 5c4c08f6f1 [Misc] Auto fallback to float16 for pre-Ampere GPUs when detected bfloat16 config (#17265) 
Signed-off-by: Isotr0py <2037008807@qq.com>
 2025-05-09 17:16:12 +00:00
Harry Mellor d6484ef3c3 Add full API docs and improve the UX of navigating them (#17485) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-05-03 19:42:43 -07:00
Jade Zheng 30215ca61f [MISC] Use string annotation types for class definitions (#17244) 
Signed-off-by: Jade Zheng <zheng.shoujian@outlook.com>
 2025-04-27 08:39:57 +00:00
Michael GoinandAurick Qiao 986537f1c3 [V1] V1 FlashInfer Attention (#16684) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Aurick Qiao <qiao@aurick.net>
 2025-04-22 00:38:41 +00:00
Joe Runde cb391d85dc [Hardware] add platform-specific request validation api (#16291) 
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
 2025-04-09 12:50:01 -07:00