Commit Graph
59 Commits
Author SHA1 Message Date
Lu Fang 7678fcd5b6 Fix the torch version parsing logic (#15857) 2025-04-10 07:37:47 -07:00
Charlie Fu e85829450d [Feature][ROCm]Enable fusion pass for torch.compile on ROCm (#15050)
Signed-off-by: charlifu <charlifu@amd.com>
2025-03-31 04:42:18 -07:00
Luka Govedič 04437e313d [Bugfix] [torch.compile] Add Dynamo metrics context during compilation (#15639)
Signed-off-by: luka <luka@neuralmagic.com>
2025-03-28 14:01:09 -06:00
Jee Jee Li 70f2c2a709 [Bugfix] Fix 'InductorAdaptor object has no attribute 'cache_dir' (#15674)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-03-28 17:10:40 +08:00
Richard Zouandyoukaichao 6278bc829e Fix incorrect filenames in vllm_compile_cache.py (#15494)
Signed-off-by: <zou3519@gmail.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
2025-03-27 18:33:41 +08:00
Matthew Vine 7a6d45bc8a Support FIPS enabled machines with MD5 hashing (#15299)
Signed-off-by: Matthew Vine <32849887+MattTheCuber@users.noreply.github.com>
2025-03-26 20:19:46 -04:00
Luka Govedič f622dbcf39 [Fix] [torch.compile] Improve UUID system for custom passes (#15249)
Signed-off-by: luka <luka@neuralmagic.com>
2025-03-24 01:54:07 +00:00
DefTruth 6ebaf9ac71 [Bugfix] consider related env vars for torch.compiled cache hash (#14953)
Signed-off-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
2025-03-23 15:53:09 +00:00
Jee Jee Li 2fa0e1396b [Bugfix] Fix torch.compile raise FileNotFoundError (#15278)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-03-22 13:49:34 +08:00
Harry Mellor 3b352a2f92 Correct capitalisation: VLLM -> vLLM (#14562)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-03-10 16:36:21 +00:00
youkaichao c6359e8ca6 [v1] torch.compile integration explanation (#14437)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-03-08 01:55:50 +08:00
Tyler Michael Smith 72c62eae5f [V1] EP/TP MoE + DP Attention (#13931) 2025-03-04 21:27:26 -08:00
Luka Govedič bd56c983d6 [torch.compile] Fix RMSNorm + quant fusion in the non-cutlass-fp8 case, rename RedundantReshapesPass to NoopEliminationPass (#10902)
Signed-off-by: luka <luka@neuralmagic.com>
2025-02-28 16:20:11 -07:00
youkaichao 09b95e36ab [torch.compile] PyTorch 2.6 and nightly compatibility (#12393)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-02-07 01:09:07 +08:00
Russell Bryant e489ad7a21 [Misc] Add SPDX-License-Identifier headers to python source files (#12628)
- **Add SPDX license headers to python source files**
- **Check for SPDX headers using pre-commit**

commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745
Author: Russell Bryant <rbryant@redhat.com>
Date:   Fri Jan 31 14:18:24 2025 -0500

    Add SPDX license headers to python source files
    
This commit adds SPDX license headers to python source files as
recommended to
the project by the Linux Foundation. These headers provide a concise way
that is
both human and machine readable for communicating license information
for each
source file. It helps avoid any ambiguity about the license of the code
and can
    also be easily used by tools to help manage license compliance.
    
The Linux Foundation runs license scans against the codebase to help
ensure
    we are in compliance with the licenses of the code we use, including
dependencies. Having these headers in place helps that tool do its job.
    
    More information can be found on the SPDX site:
    
    - https://spdx.dev/learn/handling-license-info/
    
    Signed-off-by: Russell Bryant <rbryant@redhat.com>

commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea
Author: Russell Bryant <rbryant@redhat.com>
Date:   Fri Jan 31 14:36:32 2025 -0500

    Check for SPDX headers using pre-commit
    
    Signed-off-by: Russell Bryant <rbryant@redhat.com>

---------

Signed-off-by: Russell Bryant <rbryant@redhat.com>
2025-02-02 11:58:18 -08:00
youkaichao 6e650f56a1 [torch.compile] decouple compile sizes and cudagraph sizes (#12243)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-01-24 02:01:30 +08:00
youkaichao c81081fece [torch.compile] transparent compilation with more logging (#12246)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-01-21 19:32:55 +08:00
youkaichao 51ef828f10 [torch.compile] fix sym_tensor_indices (#12191)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-01-20 11:37:50 +08:00
81763c58a0 [V1] Add V1 support of Qwen2-VL (#12128)
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: imkero <kerorek@outlook.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-19 19:52:13 +08:00
youkaichao e66faf4809 [torch.compile] store inductor compiled Python file (#12182)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-01-19 16:27:26 +08:00
youkaichao 7b98a65ae6 [torch.compile] disable logging when cache is disabled (#12043)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-01-17 20:29:31 +00:00
youkaichao f12141170a [torch.compile] consider relevant code in compilation cache (#11614)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-01-08 10:46:43 +00:00
youkaichao 3682e33f9f [v1] fix compilation cache (#11598)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-30 04:24:12 +00:00
youkaichao dba4d9dec6 [v1][bugfix] fix cudagraph with inplace buffer assignment (#11596)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-29 09:03:49 +00:00
youkaichao eb881ed006 [misc] fix typing (#11540)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-27 11:05:08 +08:00
Lucas Tuckerandlucast2021 dbeac95dbb Mypy checking for vllm/compilation (#11496)
Signed-off-by: lucast2021 <lucast2021@headroyce.org>
Co-authored-by: lucast2021 <lucast2021@headroyce.org>
2024-12-26 05:04:07 +00:00
youkaichaoandTyler Michael Smith 88a412ed3d [torch.compile] fast inductor (#11108)
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
2024-12-16 16:15:22 -08:00
Luka GovedičandVarun Sundar Rabindranath 30870b4f66 [torch.compile] Dynamic fp8 + rms_norm fusion (#10906)
Signed-off-by: luka <luka@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
2024-12-13 03:19:23 +00:00
youkaichao 66aaa7722d [torch.compile] remove graph logging in ci (#11110)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-11 10:59:50 -08:00
youkaichao 91642db952 [torch.compile] use depyf to dump torch.compile internals (#10972)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-11 10:43:05 -08:00
youkaichao d1c2e15eb3 [torch.compile] add dynamo time tracking (#11005)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-08 23:09:04 -08:00
youkaichao a1887f2c96 [torch.compile] fix deprecated code (#10948)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-06 11:01:23 +00:00
youkaichaoandWoosuk Kwon b031a455a9 [torch.compile] add logging for compilation time (#10941)
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-12-06 10:07:15 +00:00
youkaichao db87eb6c67 [torch.compile] use size tuning for specific sizes (#10933)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-05 20:30:41 -08:00
youkaichao dc5ce861bf [torch.compile] remove compilation_context and simplify code (#10838)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-03 06:19:02 +00:00
Cyrus Leung f877a7d12a [Misc] Improve type annotations for support_torch_compile (#10763)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-11-30 17:48:35 -08:00
youkaichao 05d1f8c9c6 [misc] move functions to config.py (#10624)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-25 09:27:30 +00:00
youkaichao 65813781a2 [torch.compile] add warning for unsupported models (#10622)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-24 23:27:51 -08:00
Luka Govedič 8b0fe06c89 [torch.compile] Inductor code caching fix (#10273)
Signed-off-by: luka <luka@neuralmagic.com>
Signed-off-by: Luka Govedic <luka.govedic@gmail.com>
2024-11-20 21:44:57 -08:00
youkaichao 0cd3d9717e [7/N] torch.compile, reduce compilation time (#10460)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-20 11:20:38 -08:00
youkaichao 51bb12d17b [4/N][torch.compile] clean up set_torch_compile_backend (#10401)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-17 23:57:20 -08:00
youkaichao 4fd9375028 [2/N][torch.compile] make compilation cfg part of vllm cfg (#10383)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-16 18:02:14 -08:00
Tyler Michael Smith 2885ba0e24 [Misc] Change RedundantReshapesPass and FusionPass logging from info to debug (#10308)
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
2024-11-15 02:44:26 +00:00
youkaichao eea55cca5b [1/N] torch.compile user interface design (#10237)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-11 18:01:06 -08:00
youkaichaoandWoosuk Kwon 330e82d34a [v1][torch.compile] support managing cudagraph buffer (#10203)
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-11-11 11:10:27 -08:00
bnellnm 10b67d865d [Bugfix] SymIntArrayRef expected to contain concrete integers (#10170)
Signed-off-by: Bill Nell <bill@neuralmagic.com>
2024-11-08 14:44:18 -08:00
Luka Govedičandyoukaichao 4f93dfe952 [torch.compile] Fuse RMSNorm with quant (#9138)
Signed-off-by: luka <luka@neuralmagic.com>
Co-authored-by: youkaichao <youkaichao@126.com>
2024-11-08 21:20:08 +00:00
Woosuk Kwon 4089985552 [V1] Integrate Piecewise CUDA graphs (#10058)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-11-05 22:16:04 -08:00
youkaichao c4cacbaa7f [v1] reduce graph capture time for piecewise cudagraph (#10059)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-05 18:19:50 -08:00
youkaichao ca9844b340 [bugfix] fix weak ref in piecewise cudagraph and tractable test (#10048)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-11-05 14:49:20 -08:00