iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
6,003 Commits 3 Branches 0 Tags
ed2e464653ab552c54c6da5c2b69d31bd61ba765
Commit Graph
87 Commits
Author SHA1 Message Date
Lei Wangandxinyuxiao 8d32dc603d [Kernel] Support Microsoft Runtime Kernel Lib for our Low Precision Computation - BitBLAS (#6036) 
Signed-off-by: xinyuxiao <xinyuxiao2024@gmail.com>
Co-authored-by: xinyuxiao <xinyuxiao2024@gmail.com>
 2025-04-22 09:01:36 +01:00
Charlie FuandTyler Michael Smith 188b7f9b8c [Performance][ROCm] Add skinny gemms for unquantized linear on ROCm (#15830) 
Signed-off-by: charlifu <charlifu@amd.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
 2025-04-21 20:46:22 -07:00
Dipika Sikka 54a66e5fee [Misc] Update compressed-tensors WNA16 to support zero-points (#14211) 2025-04-15 07:33:51 -06:00
Jinzhen LinMichael Goinmgoin
 		d06ba4ed3f [Kernel] moe wna16 marlin kernel (#14447) 
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-04-14 20:05:22 -07:00
Michael Goin f41647ee6b [Kernel] Support W8A8 channel-wise weights and per-token activations in triton fused_moe_kernel (#16366) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-04-11 17:54:08 +00:00
Jinzhen Lin 2fa66ef713 [Bugfix] fix use_atomic_add support of marlin kernel when using v1 engine (#15946) 
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
 2025-04-05 20:04:22 -07:00
Gregory ShtrasbergandLuka Govedič 4d0ec37267 [Quantization][FP8] Adding support for fp8 gemm layer input in fp8 (#14578) 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
 2025-03-28 02:58:16 +00:00
ElizaWszolaandLucas Wilkinson 9239bf718e [Kernel] CUTLASS grouped gemm fp8 MoE kernel (#13972) 
Signed-off-by: ElizaWszola <eliza@neuralmagic.com>
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Co-authored-by: Lucas Wilkinson <wilkinson.lucas@gmail.com>
 2025-03-27 00:54:44 +00:00
DefTruth f90d34b498 [Misc] Add tuned R1 w8a8 and MoE configs for NVIDIA L20 (#15322) 
Signed-off-by: DefTruth <qiustudent_r@163.com>
 2025-03-23 01:10:10 -07:00
ekuznetsov139 8b793f7ec6 MI325 configs, fused_moe_kernel bugfix (#14987) 
Signed-off-by: Eugene Kuznetsov <eugene.kuznetsov@amd.com>
 2025-03-18 08:05:18 -07:00
Simon Mo 71c1e07107 [Kernel] Add more tuned configs (#14877) 
Signed-off-by: simon-mo <simon.mo@hey.com>
 2025-03-15 20:25:03 -07:00
Lucas Wilkinson 9532c49836 [Attention] MLA get rid of materialization (#14770) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-03-13 23:39:02 -07:00
Jeff Daily a1c8f3796c dynamic distpatch of fp8 kernels (#14245) 
Signed-off-by: Jeff Daily <jeff.daily@amd.com>
 2025-03-11 10:54:56 -04:00
Jinzhen Lin d0feea31c7 [Kernel] optimize performance of gptq marlin kernel when n is small (#14138) 
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
 2025-03-07 11:53:38 -05:00
Luka Govedič e1744502c2 [FP8] Refactor apply_fp8_linear and apply_fp8_linear_generic into an object (#14390) 
Signed-off-by: luka <luka@neuralmagic.com>
 2025-03-07 05:20:16 +00:00
YajieWang 6a92ff93e1 [Misc][Kernel]: Add GPTQAllSpark Quantization (#12931) 2025-02-28 22:30:59 -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
Woosuk Kwon b382a7f28f [BugFix] Make FP8 Linear compatible with torch.compile (#13918) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-02-26 13:48:55 -08:00
cjackal 51010a1807 [Misc] set single whitespace between log sentences (#13771) 
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
 2025-02-25 10:26:12 +08:00
Gregory Shtrasberg c904fdddf6 [ROCm] Apply FP8 weights padding to values not divisible by 512 bytes on ROCm (#13231) 2025-02-22 05:54:38 -08:00
Lucas WilkinsonPatrick Hornsimon-moTyler Michael Smith
 		288cc6c234 [Attention] MLA with chunked prefill (#12639) 
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Patrick Horn <patrick.horn@gmail.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2025-02-21 15:30:12 -08:00
Tyler Michael Smith b3942e157e [Bugfix][CI][V1] Work around V1 + CUDA Graph + torch._scaled_mm fallback issue (#13425) 
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2025-02-18 00:32:48 +00:00
rasmith ed0de3e4b8 [AMD] [Model] DeepSeek tunings (#13199) 2025-02-15 03:58:09 -08:00
Michael Goin 09972e716c [Bugfix] Allow fallback to AWQ from AWQMarlin at per-layer granularity (#13119) 2025-02-12 09:19:53 -08:00
Qubitium-ModelCloud 36a08630e8 [CORE] [QUANT] Support for GPTQModel's dynamic quantization per module override/control (#7086) 2025-02-12 09:19:43 -08:00
TJian eaa92d4437 [ROCm] [Feature] [Doc] [Dockerfile] [BugFix] Support Per-Token-Activation Per-Channel-Weight FP8 Quantization Inferencing (#12501) 2025-02-07 08:13:43 -08:00
Lu Fang 741429a4cd [MISC] Check space in the file names in the pre commit checks (#12804) 
Signed-off-by: Lu Fang <lufang@fb.com>
 2025-02-06 15:36:21 -08:00
Lu Fang 9cdea30b4f [Misc][Easy] Remove the space from the file name 2025-02-05 19:23:35 -08:00
Lucas Wilkinson 76abd0c881 [Bugfix] Better FP8 supported defaults 2025-02-05 19:22:19 -08:00
Kyle Sayersandmgoin 7ff7a638b6 [Model][Quant] Fix GLM, Fix fused module mappings for quantization (#12634) 
Signed-off-by: mgoin <michael@neuralmagic.com>
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
 2025-02-05 05:32:06 +00:00
Hongxia YangandMatthew Wong c36ac98d01 [AMD][ROCm] Enable DeepSeek model on ROCm (#12662) 
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Co-authored-by: Matthew Wong <Matthew.Wong2@amd.com>
 2025-02-04 08:24:11 +00:00
kushanam 4797dad3ec [Model] Add Deepseek V3 fp8_w8a8 configs for B200 (#12707) 2025-02-03 13:30:39 -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
Lucas WilkinsonWoosuk Kwonsimon-moMichael GoinZhuohan LiTyler Michael SmithAlexander Matveev
 		baeded2569 [Attention] Deepseek v3 MLA support with FP8 compute (#12601) 
This PR implements the Deepseek V3 support by performing matrix absorption the fp8 weights 

---------

Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: simon-mo <simon.mo@hey.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Alexander Matveev <59768536+alexm-neuralmagic@users.noreply.github.com>
 2025-01-31 21:52:51 -08:00
Tyler Michael Smith eb5741ad42 [Kernel][Quantization] Integrate block-quantized CUTLASS kernels for DeepSeekV3 (#12587) 
Integrates the block-quantized kernels introduced in
https://github.com/vllm-project/vllm/pull/11868 for use in linear
layers.

Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2025-01-31 15:29:11 -08:00
Robert Shawmgoinsimon-mo
 		9b0c4bab36 [Kernel] Triton Configs for Fp8 Block Quantization (#11589) 
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Signed-off-by: mgoin <michael@neuralmagic.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
 2025-01-30 11:53:22 -08:00
Harry Mellor 823ab79633 Update pre-commit hooks (#12475) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-01-27 17:23:08 -07:00
Gregory Shtrasberg b5b57e301e [AMD][FP8] Using MI300 FP8 format on ROCm for block_quant (#12134) 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
 2025-01-17 17:12:26 +00:00
Cyrus LeungandMaxime Fournioux d848800e88 [Misc] Move print_*_once from utils to logger (#11298) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Maxime Fournioux <55544262+mfournioux@users.noreply.github.com>
Co-authored-by: Maxime Fournioux <55544262+mfournioux@users.noreply.github.com>
 2025-01-09 12:48:12 +08:00
Robert ShawandWoosuk Kwon 56fe4c297c [TPU][Quantization] TPU W8A8 (#11785) 
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-01-08 19:33:29 +00:00
Michael Goinsimon-mosimon-moHandH1998
 		2072924d14 [Model] [Quantization] Support deepseek_v3 w8a8 fp8 block-wise quantization (#11523) 
Signed-off-by: mgoin <michael@neuralmagic.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
Signed-off-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: simon-mo <simon.mo@hey.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: HandH1998 <1335248067@qq.com>
 2024-12-26 15:33:30 -08:00
Isotr0py 276738ce0f [Bugfix] Fix broken CPU compressed-tensors test (#11338) 
Signed-off-by: Isotr0py <2037008807@qq.com>
 2024-12-19 17:37:31 +00:00
Tyler Michael Smith 5a9da2e6e9 [Bugfix][Build/CI] Fix sparse CUTLASS compilation on CUDA [12.0, 12.2) (#11311) 
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2024-12-19 02:43:30 +00:00
ElizaWszola b00b33d77e [Model][Quantization] HQQ support through Marlin kernel expansion (#9766) 
Signed-off-by: ElizaWszola <eliza@neuralmagic.com>
 2024-11-19 13:31:12 -08:00
Lucas Wilkinson 96d999fbe8 [Kernel] Initial Machete W4A8 support + Refactors (#9855) 
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
 2024-11-18 12:59:29 -07:00
Luka GovedičandDaniël de Kok bf2ddc6610 [bugfix] Fix static asymmetric quantization case (#10334) 
Signed-off-by: Daniël de Kok <me@danieldk.eu>
Signed-off-by: luka <luka@neuralmagic.com>
Co-authored-by: Daniël de Kok <me@danieldk.eu>
 2024-11-15 09:35:11 +08:00
Michael Goin 4ab3256644 [Bugfix] Fix FP8 torch._scaled_mm fallback for torch>2.5 with CUDA<12.4 (#10095) 
Signed-off-by: mgoin <michael@neuralmagic.com>
 2024-11-07 00:54:13 +00:00
Michael Goin 226688bd61 [Bugfix][VLM] Make apply_fp8_linear work with >2D input (#9812) 2024-10-29 19:49:44 -07:00
wangshuai09 4e2d95e372 [Hardware][ROCM] using current_platform.is_rocm (#9642) 
Signed-off-by: wangshuai09 <391746016@qq.com>
 2024-10-28 04:07:00 +00:00
Lucas Wilkinson e312e52b44 [Kernel] Add Exllama as a backend for compressed-tensors (#9395) 2024-10-17 09:48:26 -04:00