biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
8,643 Commits 2 Branches 140 Tags
94096a47c92c4a53ad44cfffdca918669c0f89e0
Commit Graph

110 Commits

Author SHA1 Message Date
Michael Goin
94096a47c9 [UX] Separate marlin moe config logic from triton moe (#23006) 2025-08-16 22:16:42 -04:00
bnellnm
8ad7285ea2 [Kernels] Clean up FusedMoeMethodBase and modular kernel setup. Remove extra arguments from modular kernel methods. (#22035) 
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2025-08-15 14:46:00 -04:00
amirkl94
b4cef5e6c7 refactor: Change scaling factors calculation for flashinfer FusedMoE (#22812) 
Signed-off-by: Amir Klein <203507526+amirkl94@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2025-08-15 06:19:31 +00:00
Simon Mo
f1f0d2fab8 Revert "[Kernel] Add cuda kernel for gpt_oss activation" (#22948) 2025-08-14 17:38:10 -07:00
Jee Jee Li
81f4b96481 [Kernel] Add cuda kernel for gpt_oss activation (#22538) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-08-14 17:21:29 -07:00
Chi Zhang
98deac3879 [FEATURE] support custom vllm tuned config path for fused moe triton kernels (#22791) 
Signed-off-by: Chi Zhang <zhangchi.usc1992@bytedance.com>
 2025-08-13 20:27:25 +08:00
Wentao Ye
f7dcce7a4a [Feature] Add VLLM_USE_DEEP_GEMM_E8M0 Env to Control E8M0 Scale (#21968) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-08-11 09:39:08 -07:00
Isotr0py
7e8d685775 [Minor] Fix pre-commit error on main (#22579) 
Signed-off-by: Isotr0py <2037008807@qq.com>
 2025-08-10 00:08:23 -07:00
Jee Jee Li
0c5254b82a [oss] Init gpt-oss bf16 support (#22508) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-08-09 20:19:13 -07:00
Varun Sundar Rabindranath
f703b923f3 [Misc] DeepGEMM : Avoid JIT generation in the hot-path (#22215) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-08-08 16:09:59 -07:00
Wentao Ye
d7b28f3415 [Log] DeepGEMM Update Log for Unaligned Problem Size (#22208) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-08-04 19:13:19 -07:00
JartX
3654847db5 feat: Add Support GPTQ Quantization MOE on ROCM vllm serve (#21733) 2025-08-01 21:12:19 -04:00
amirkl94
207b750e19 [NVIDIA] Add SM100 Flashinfer MoE per tensor scale fp8 backend (#21458) 
Signed-off-by: Amir Klein <203507526+amirkl94@users.noreply.github.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-07-31 06:00:01 -07:00
Isotr0py
a4528f0cac [Model]: Fused MoE for nomic-embed-text-v2-moe (#18321) 
Signed-off-by: isotr0py <2037008807@qq.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-07-29 03:13:27 -07:00
Kaixi Hou
de509ae8eb [NVIDIA] Explicitly disable shuffled weights for flashinfer blockscale moe fp8 kernels (#21411) 
Signed-off-by: kaixih <kaixih@nvidia.com>
 2025-07-26 07:10:36 -07:00
Kaixi Hou
6d0734c562 [NVIDIA] Add SM100 Flashinfer MoE blockscale fp8 backend for low latency (#20645) 
Signed-off-by: kaixih <kaixih@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-07-19 02:33:01 -07:00
Richard Zou
b2eb2b5ad7 [Kernel] Apply torch.Tag.needs_fixed_stride_order only for torch==2.6.0 (#19346) 
Signed-off-by: rzou <zou3519@gmail.com>
 2025-07-18 14:10:21 -04:00
Shu Wang
c7d8724e78 [Core] FlashInfer CUTLASS fused MoE backend (NVFP4) (#20037) 
Signed-off-by: shuw <shuw@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-07-17 21:32:45 -07:00
Varun Sundar Rabindranath
11dfdf21bf [Kernel] DeepGemm MoE : Integrate triton permute / unpermute kernels (#20903) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-07-17 08:10:37 +00:00
Peter Pan
1eb2b9c102 [CI] update typos config for CI pre-commit and fix some spells (#20919) 
Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>
 2025-07-15 21:12:40 -07:00
Varun Sundar Rabindranath
c0569dbc82 [Misc] ModularKernel : Perform WeightAndReduce inside TritonExperts & DeepGemmExperts (#20725) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-07-14 19:47:16 +00:00
Wentao Ye
e2de455c34 [Feature] Integrate SM100 DeepGEMM support (#20087) 2025-07-10 20:18:05 -07:00
Duncan Moss
5923ab9524 [fix]: disable cutlass block scaled group gemm for EP (#20781) 
Signed-off-by: Duncan Moss <djm.moss@gmail.com>
 2025-07-11 02:39:18 +00:00
Varun Sundar Rabindranath
f0c98cae27 [Misc] MoE ModularKernel : Introduce TopKWeightAndReduce (#20648) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-07-10 14:40:38 -07:00
Varun Sundar Rabindranath
805d62ca88 [Misc] DP : Add ExpertTokensMetadata (#20332) 
Signed-off-by: Varun <vsundarr@redhat.com>
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun <vsundarr@redhat.com>
 2025-07-10 00:33:14 +00:00
fxmarty-amd
332d4cb17b [Feature][Quantization] MXFP4 support for MOE models (#17888) 
Signed-off-by: Felix Marty <felmarty@amd.com>
Signed-off-by: Bowen Bao <bowenbao@amd.com>
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Co-authored-by: Bowen Bao <bowenbao@amd.com>
 2025-07-09 13:19:02 -07:00
Duncan Moss
97abeb1daa [feat] enable SM100 CUTLASS block scaled group gemm for smaller batch sizes (#20640) 
Signed-off-by: Duncan Moss <djm.moss@gmail.com>
 2025-07-09 11:03:35 +08:00
Duncan Moss
3d184b95b8 [feat]: CUTLASS block scaled group gemm for SM100 (#19757) 
Signed-off-by: Duncan Moss <djm.moss@gmail.com>
Co-authored-by: Duncan Moss <dmoss@nvidia.com>
 2025-07-04 12:58:04 -06:00
bnellnm
78fe77534b [Kernel] Enable fp8 support for pplx and BatchedTritonExperts. (#18864) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2025-07-03 14:55:40 -07:00
bnellnm
c1909e7e8c [Kernels] MoE refactor (#19636) 
Signed-off-by: Bill Nell <bnell@redhat.com>
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Co-authored-by: ElizaWszola <ewszola@redhat.com>
 2025-07-02 06:08:27 -07:00
bnellnm
015fab8c2f [Kernels][Bugfix] Use torch op for all kernels in FusedMoE forward. Add additional testing for cudagraphs. (#19717) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2025-06-24 23:22:58 -07:00
Varun Sundar Rabindranath
e3b12667d4 [BugFix] : Fix Batched DeepGemm Experts (#19515) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-06-12 20:43:02 -06:00
bnellnm
29fa5cac1c [Kernels] Add activation chunking logic to FusedMoEModularKernel (#19168) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2025-06-11 12:53:10 -04:00
ElizaWszola
84166fee97 [Kernel] Integrate CUTLASS MoE kernel with PPLX (#18762) 
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2025-06-06 18:26:11 -07:00
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