biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
6,918 Commits 2 Branches 140 Tags
fa98d77773c649de05a4bda9847682c80287aa36
Commit Graph

76 Commits

Author SHA1 Message Date
Varun 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
bnellnm
f9c069c85e Modularize fused experts and integrate PPLX kernels (#15956) 2025-05-14 13:11:54 -07:00
TJian
612c2edb4f [FEAT] [ROCm]: Add AITER CK 2 Stages MoE support (#17110) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
 2025-05-14 03:03:11 -07:00
Harry Mellor
6223dd8114 Update deprecated type hinting in model_executor/layers (#18056) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-05-13 04:17:23 -07:00
Hongxia Yang
ed3a1d2106 [ROCm] fix num_stages for default moe config to avoid triton OutOfResource error (#17744) 
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
 2025-05-07 00:39:48 +00:00
Mengqing Cao
f9bc5a0693 [Bugfix] Fix triton import with local TritonPlaceholder (#17446) 
Signed-off-by: Mengqing Cao <cmq0113@163.com>
 2025-05-06 17:53:09 +08:00
Caleb_Du
3e887d2e0c permute/unpermute kernel for moe optimization (#14568) 
Signed-off-by: Caleb_Du <Caleb_Du@zju.edu.cn>
 2025-05-02 11:31:55 -07:00
kliuae
5b794cae8d [ROCm] Add aiter tkw1 kernel for Llama4 fp8 (#16727) 
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-04-21 20:42:34 -07:00
Jinzhen Lin
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
TJian
2976dc27e9 [Bug] [ROCm] Fix Llama 4 Enablement Bug on ROCm: V0 ROCmFlashAttentionImpl and Triton Fused MoE bugs (#16198) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
Co-authored-by: Hongxia Yang <hongxia.yang@amd.com>
Co-authored-by: kliuae <kuanfu.liu@embeddedllm.com>
 2025-04-08 19:12:34 -07:00
Lu Fang
55dcce91df Upstream Llama4 Support to Main (#16113) 
Signed-off-by: Aston Zhang <22279212+astonzhang@users.noreply.github.com>
Signed-off-by: Chris Thi <chris.c.thi@gmail.com>
Signed-off-by: drisspg <drisspguessous@gmail.com>
Signed-off-by: Jon Swenson <jmswen@gmail.com>
Signed-off-by: Keyun Tong <tongkeyun@gmail.com>
Signed-off-by: Lu Fang <fanglu@meta.com>
Signed-off-by: Xiaodong Wang <xdwang@meta.com>
Signed-off-by: Yang Chen <yangche@fb.com>
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
Signed-off-by: Zijing Liu <liuzijing2014@gmail.com>
Signed-off-by: Lu Fang <lufang@fb.com>
Signed-off-by: Lu Fang <fanglu@fb.com>
Signed-off-by: Lucia Fang <fanglu@fb.com>
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Lu Fang <fanglu@fb.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-04-07 08:06:27 -07:00
bnellnm
d6fc629f4d [Kernel][Minor] Re-fuse triton moe weight application (#16071) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2025-04-04 23:27:34 +00:00
bnellnm
15ba07ef25 [Minor] Fused experts refactor (#15914) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2025-04-03 10:19:38 -07:00
bnellnm
e59ca942f5 Add option to use DeepGemm contiguous grouped gemm kernel for fused MoE operations. (#13932) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2025-04-01 12:07:43 -04:00
Wes
4ae17bf1e2 Revert "Use Cache Hinting for fused_moe kernel (#15511)" (#15645) 
Signed-off-by: Wes Medford <wryanmedford@gmail.com>
 2025-03-27 19:45:55 -07:00
ElizaWszola
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
Wes
7a888271f5 Use Cache Hinting for fused_moe kernel (#15511) 2025-03-26 23:21:34 +00:00
vllmellm
5ebf66748b [FEAT][ROCm] Integrate Fused MoE Kernels from AITER (#14967) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-03-26 16:30:30 +08:00
Gregory Shtrasberg
f533b5837f [ROCm][Kernel] MoE weights padding (#14454) 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Signed-off-by: charlifu <charlifu@amd.com>
Co-authored-by: charlifu <charlifu@amd.com>
 2025-03-24 23:45:30 +00:00
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
Jinzhen Lin
90e88ab756 [Kernel] moe wna16 cuda kernel (#13321) 
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-03-10 20:12:40 -04:00
Michael Goin
19d98e0c7d [Kernel] Optimize moe intermediate_cache usage (#13625) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-03-03 16:29:53 -05:00
Michael Goin
07c4353057 [Model] Support Grok1 (#13795) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-02-26 01:07:12 +00:00
Michael Goin
db986c19ea Fix precommit fail in fused_moe intermediate_cache2 chunking (#13772) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-02-24 09:25:47 -08:00
Zhonghua Deng
ccc00515fd [BugFix] Illegal memory access for MoE On H20 (#13693) 2025-02-24 07:37:32 -08:00
Jongseok Park
781096e385 Expert Parallelism (EP) Support for DeepSeek V2 (#12583) 2025-02-24 07:33:20 -08:00
chenxiaobing
ed6e9075d3 [Bugfix] Fix deepseekv3 grouped topk error (#13474)
Some checks failed
Create Release / Create Release (push) Has been cancelled
Details 
Signed-off-by: Chen-XiaoBing <chenxb002@whu.edu.cn>
 2025-02-20 06:47:01 -08:00
Michael Goin
2344192a55 Optimize moe_align_block_size for deepseek_v3 (#12850) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-02-13 18:43:37 -05:00
Lu Fang
9cdea30b4f [Misc][Easy] Remove the space from the file name 2025-02-05 19:23:35 -08:00
Yang Chen
95460fc513 [Kernel] port sgl moe_align_block_size kernels (#12574) 
sgl_moe_align_block_size is based on:


ded9fcd09a

moe_align_block_size is based on:


ba5112ff69

Signed-off-by: Yang Chen <yangche@fb.com>
 2025-02-03 13:09:50 +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
Michael Goin
3194039c0e Apply torch.compile to fused_moe/grouped_topk (#12637) 2025-02-01 16:16:19 +00:00
Robert Shaw
145c2ff648 [Bugfix] Revert MoE Triton Config Default (#12629) 
SUMMARY:
* previous PR for pulling in block configs also changed defaults
(https://github.com/vllm-project/vllm/pull/11589/files) for FP8
* this broke L4 MoE since there was not enough SHM for the default
configuration
* this reverts the non-block example to the default

Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
 2025-01-31 15:28:47 -08:00
Robert Shaw
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
Jinzhen Lin
27b78c73ca [Kernel] add triton fused moe kernel for gptq/awq (#12185) 2025-01-29 09:07:09 -05:00
Steve Luo
f35ec461fc [Bugfix] Fix deepseekv3 gate bias error (#12002) 
Signed-off-by: mgoin <michael@neuralmagic.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
 2025-01-13 13:43:51 -07:00
shaochangxu
c32a7c7c0c [Bugfix] fused_experts_impl wrong compute type for float32 (#11921) 
Signed-off-by: shaochangxu.scx <shaochangxu.scx@antgroup.com>
Co-authored-by: shaochangxu.scx <shaochangxu.scx@antgroup.com>
 2025-01-11 13:49:39 +08:00
youkaichao
869579a702 [optimization] remove python function call for custom op (#11750) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-01-07 17:04:28 +00:00
Simon Mo
f49777ba62 Deepseek v3 (#11502)
Some checks failed
Create Release / Create Release (push) Has been cancelled
Details 
Signed-off-by: mgoin <michael@neuralmagic.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
Co-authored-by: robertgshaw2-neuralmagic <rshaw@neuralmagic.com>
 2024-12-26 16:09:44 -08:00
Michael Goin
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
rasmith
1d75472626 [BugFix] [Kernel] Fix GPU SEGV occuring in fused_moe kernel (#10385) 
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
 2024-11-16 09:55:05 +00:00
youkaichao
96e0c9cbbd [torch.compile] directly register custom op (#9896) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2024-10-31 21:56:09 -07:00
youkaichao
32176fee73 [torch.compile] support moe models (#9632) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2024-10-27 21:58:04 -07:00
Charlie Fu
59449095ab [Performance][Kernel] Fused_moe Performance Improvement (#9384) 
Signed-off-by: charlifu <charlifu@amd.com>
 2024-10-24 15:37:52 -07:00
Divakar Verma
01843c89b8 [Misc] log when using default MoE config (#8971) 2024-10-03 04:31:07 +00:00
ElizaWszola
a091e2da3e [Kernel] Enable 8-bit weights in Fused Marlin MoE (#8032) 
Co-authored-by: Dipika <dipikasikka1@gmail.com>
 2024-09-16 09:47:19 -06:00
Dipika Sikka
8f44a92d85 [BugFix] fix group_topk (#8430) 2024-09-13 09:23:42 +08:00
Dipika Sikka
6cd5e5b07e [Misc] Fused MoE Marlin support for GPTQ (#8217) 2024-09-09 23:02:52 -04:00