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
117 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
Gregory Shtrasberg 031ca762d7 [ROCm][Bugfix] Compilation passes fix (#22202) 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
 2025-08-04 19:12:28 -07:00
Xiao 554df8a6a2 Revert "[compile][startup] Disable C++ compilation of symbolic shapes" (#22122) 
Signed-off-by: Xiao Liu <xiszishu@gmail.com>
 2025-08-02 09:03:30 -07:00
Animesh Jain 9659bc7f27 [compile][startup] Disable C++ compilation of symbolic shapes (#20836) 
Signed-off-by: Animesh Jain <anijain@umich.edu>
 2025-08-01 10:38:52 -07:00
Richard Zou 8026a335a1 [BugFix] Update AttnFusionPass cache key (#21947) 
Signed-off-by: Richard Zou <zou3519@gmail.com>
 2025-08-01 07:11:29 -07:00
TJian 26b5f7bd2a [BUG] [ROCm] Fix import bug on ROCm (#22083) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-08-01 05:25:20 -07:00
Ilya Markovandilmarkov 6e672daf62 Add FlashInfer allreduce RMSNorm Quant fusion (#21069) 
Signed-off-by: ilmarkov <imarkov@redhat.com>
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: ilmarkov <imarkov@redhat.com>
 2025-07-31 13:58:38 -07:00
Zhengxu Chen 7349d5268b [ez] Remove a trailing space from compilation/decorators.py (#22028) 2025-07-31 09:46:07 -07:00
cascade 287f527f54 [Feature] Add async tensor parallelism for scaled mm (#20155) 
Signed-off-by: cascade812 <cascade812@outlook.com>
 2025-07-30 17:23:41 -04:00
Richard Zou 04e38500ee [Bugfix] VLLM_V1 supports passing other compilation levels (#19340) 
Signed-off-by: Richard Zou <zou3519@gmail.com>
 2025-07-29 09:35:58 -04:00
Chaojun Zhang d9f9a3fd96 [XPU] Conditionally import CUDA-specific passes to avoid import errors on xpu platform (#21036) 
Signed-off-by: chzhang <chaojun.zhang@intel.com>
 2025-07-24 23:23:36 +08:00
Yong Hoon Shin 4ac7713e32 Add test case for compiling multiple graphs (#21044) 
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
 2025-07-23 11:00:47 -07:00
Xin Li ae268b6326 Fix Flashinfer Allreduce+Norm enable disable calculation based on fi_allreduce_fusion_max_token_num (#21325) 
Signed-off-by: XIn Li <xinli@nvidia.com>
 2025-07-22 12:42:31 -07:00
Ilya Markovandilmarkov 37a7d5d74a [Misc] Refactor AllReduceFusionPass. Remove parameter (#20918) 
Signed-off-by: ilmarkov <imarkov@redhat.com>
Co-authored-by: ilmarkov <imarkov@redhat.com>
 2025-07-15 06:57:40 +00:00
Boyuan Feng 91b3d190ae [cold start] replace VLLM_COMPILE_DEPYF with debug_dump_dir (#20940) 
Signed-off-by: Boyuan Feng <boyuan@meta.com>
 2025-07-15 13:02:17 +08:00
Richard Zou ba8c300018 [BugFix] VLLM_DISABLE_COMPILE_CACHE=1 should disable all reads and writes from the cache (#20942) 
Signed-off-by: Richard Zou <zou3519@gmail.com>
 2025-07-15 01:26:18 +00:00
Yong Hoon Shin 61e20828da Fall back if flashinfer comm module not found (#20936) 
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
 2025-07-14 23:11:18 +00:00
Boyuan Feng c1c8ca57ff [cold start time] add envs.VLLM_COMPILE_DEPYF to guard decompile (#20790) 
Signed-off-by: Boyuan Feng <boyuan@meta.com>
 2025-07-11 23:06:13 -07:00
Ilya Markovandilmarkov fc0f41d10a Integration SM100 FlashInfer fused allreduce RMSNorm (#20691) 
Signed-off-by: ilmarkov <imarkov@redhat.com>
Co-authored-by: ilmarkov <imarkov@redhat.com>
 2025-07-11 18:58:15 -07:00
Luka Govedič 762be26a8e [Bugfix] Upgrade depyf to 0.19 and streamline custom pass logging (#20777) 
Signed-off-by: Luka Govedic <lgovedic@redhat.com>
Signed-off-by: luka <lgovedic@redhat.com>
 2025-07-11 00:15:22 -07:00
Luka Govedičandmgoin 31d5c1797f [Perf][fp8] Use CustomOp abstraction for fp8 quant for better perf (#19830) 
Signed-off-by: Luka Govedic <lgovedic@redhat.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-07-11 04:56:28 +00:00
Kyle Yu d2e841a10a [Misc] Improve logging for dynamic shape cache compilation (#20573) 
Signed-off-by: kyolebu <kyu@redhat.com>
 2025-07-08 00:48:09 +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
Boyuan Feng c01d1c5aba use .dev for version comparison with pytorch nightly release (#20031) 
Signed-off-by: Boyuan Feng <boyuan@meta.com>
 2025-06-24 21:52:16 +00:00
cascade e6327c9b3e [Feature] Support sequence parallelism for static fp8 quantization (#19181) 
Signed-off-by: cascade812 <cascade812@outlook.com>
 2025-06-23 16:09:02 -04:00
Richard Zou ed33349738 [BugFix] Fix use_cudagraph=False (#19612) 
Signed-off-by: Richard Zou <zou3519@gmail.com>
 2025-06-19 08:23:12 +08:00
Luka Govedič 3597b06a4f [CUDA] Enable full cudagraph for FlashMLA (#18581) 
Signed-off-by: luka <luka@neuralmagic.com>
 2025-06-13 18:12:26 +00:00
youkaichao d70bc7c029 [torch.compile] reorganize the cache directory to support compiling multiple models (#19064) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-06-13 15:23:25 +08:00
Boyuan Feng ce688ad46e use base version for version comparison (#19587) 
Signed-off-by: Boyuan Feng <boyuan@meta.com>
 2025-06-13 15:09:34 +08:00
Luka GovedičandSage Moore f98548b9da [torch.compile][ROCm] Fuse quantization onto attention using a torch.compile pass (#16756) 
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Sage Moore <sage@neuralmagic.com>
 2025-06-12 08:31:04 -07:00
Richard Zou eaa2e51088 [Bugfix] Re-enable use_cudagraph in vLLM v1 (#19299) 
Signed-off-by: Richard Zou <zou3519@gmail.com>
 2025-06-08 08:56:12 +08:00
Li, Jiang 4555143ea7 [CPU] V1 support for the CPU backend (#16441) 2025-06-03 18:43:01 -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
Michael Goin cc977286e7 Reduce logs in CLI scripts and plugin loader (#18970) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-06-03 06:00:45 +00:00
Richard Zou 84ec470fca Improve "failed to get the hash of the compiled graph" error (#18956) 
Signed-off-by: rzou <zou3519@gmail.com>
 2025-05-30 15:00:54 +00:00
Richard Zou a521ef06e5 Use standalone_compile by default in torch >= 2.8.0 (#18846) 
Signed-off-by: rzou <zou3519@gmail.com>
 2025-05-30 06:41:58 +08:00
Richard Zou 26b4fa45be Add ability to use CUDAGraphs with use_inductor=False (#17345) 
Signed-off-by: rzou <zou3519@gmail.com>
 2025-05-29 10:16:52 +08:00
Richard Zou aa42561e40 Fix PiecewiseCompileInterpreter (#17338) 
Signed-off-by: rzou <zou3519@gmail.com>
 2025-05-28 08:40:53 +00:00
Hyogeun Oh (오효근) a68e293cb9 [Doc] Convert Sphinx directives ( {class}, {meth}, {attr}, ...) to MkDocs format for better documentation linking (#18663) 
Signed-off-by: Zerohertz <ohg3417@gmail.com>
 2025-05-27 01:44:20 -07:00
cascade 71ea614d4a [Feature]Add async tensor parallelism using compilation pass (#17882) 
Signed-off-by: cascade812 <cascade812@outlook.com>
 2025-05-23 01:03:34 -07:00
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
Charlie Fu 7b2f28deba [AMD][torch.compile] Enable silu+fp8_quant fusion for rocm (#18082) 
Signed-off-by: charlifu <charlifu@amd.com>
 2025-05-13 22:13:56 -07:00
Harry Mellor 19324d660c Update deprecated type hinting in vllm/compilation (#18072) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-05-13 08:32:48 -07:00
Aaron Pham cb528d0585 [Fix] check to make sure processor has chat templates (#18047) 
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
 2025-05-13 03:04:10 -07:00
Harry Mellor 4b2ed7926a Improve configs - the rest! (#17562) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-05-09 15:18:44 -07:00
Richard Zou ea2236bf95 Add option to use torch._inductor.standalone_compile (#17057) 
Signed-off-by: rzou <zou3519@gmail.com>
 2025-05-09 12:59:04 -07:00
Richard Zou edbf2d609e [easy] Fix logspam on PiecewiseBackend errors (#17138) 
Signed-off-by: rzou <zou3519@gmail.com>
 2025-05-05 23:46:11 -07:00
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
Sage Moore 460a2b1100 [torch.compile] Add torch inductor pass for fusing silu_and_mul with subsequent scaled_fp8_quant operations (#10867) 
Signed-off-by: Sage Moore <sage@neuralmagic.com>
 2025-05-01 07:59:28 -07:00
Keyun Tong 26bc4bbcd8 Avoid overwriting vllm_compile_cache.py (#17418) 
Signed-off-by: Keyun Tong <tongkeyun@gmail.com>
 2025-05-01 07:30:57 +00:00