biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
7,431 Commits 2 Branches 140 Tags
c1909e7e8ccd2037e76536a8e726120c85d3754e
Commit Graph

80 Commits

Author SHA1 Message Date
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
TJian
02cabff207 [V1] [ROCm] Enable EP with AITER Fused MoE (#20270) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-07-01 16:48:30 +00:00
Li, Jiang
6cc1e7d96d [CPU] Update custom ops for the CPU backend (#20255) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
 2025-07-01 07:25:03 +00:00
Dipika Sikka
6f2f53a82d [Quantization] Add compressed-tensors NVFP4 MoE Support (#19990) 
Signed-off-by: Dipika Sikka <dipikasikka1@gmail.com>
Signed-off-by: Dipika <dipikasikka1@gmail.com>
 2025-06-29 22:05:40 +00:00
Wentao Ye
4d36693687 [Refactor] Create a function util and cache the results for has_deepgemm, has_deepep, has_pplx (#20187) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-06-28 22:06:38 +00:00
bnellnm
c6c983053d [Bugfix] Mark 'hidden_states' as mutable in moe_forward registration. (#20152) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2025-06-27 09:42:22 -06:00
Bowen Wang
e9fd658a73 [Feature] Expert Parallelism Load Balancer (EPLB) (#18343) 
Signed-off-by: Bowen Wang <abmfy@icloud.com>
 2025-06-26 15:30:21 -07:00
Li, Jiang
0567c8249f [CPU] Fix torch version in x86 CPU backend (#19258) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
 2025-06-26 03:34:47 -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
Tyler Michael Smith
68aaeb3749 [EP+DP] Optimize the little operations in the DeepGEMM + DeepEP low latency case (#19885) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Signed-off-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-06-23 11:07:47 -07:00
Varun Sundar Rabindranath
9d880f594d [Misc] Turn MOE_DP_CHUNK_SIZE into an env var (#19506) 2025-06-12 18:01:16 +00:00
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
Tyler Michael Smith
8a57872b2a [Bugfix][EP+DP] Use pplx-kernel internode instead of intranode (#19034) 
Signed-off-by: Tyler Michael Smith <tysmith@redhat.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2025-06-03 11:36:51 +08:00
vllmellm
0f5e0d567e [FEAT][ROCm] Add AITER grouped topk for DeepSeekV2 (#18825) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-05-31 03:39:31 -07:00
Varun Sundar Rabindranath
7951d78738 [Core] Enable CUDA graphs for DP + All2All kernels (#18724) 
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
 2025-05-28 22:55:30 +00:00
vllmellm
d260f799a9 [FEAT] [ROCm] Upgrade AITER Fused MoE kernels. (#18271) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-05-26 23:14:07 -07:00
wangxiyuan
b9018a3f9f [BugFix] Fix import error for fused_moe (#18642) 
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
 2025-05-24 07:53:36 -07:00
youkaichao
6a7988c55b Refactor pplx init logic to make it modular (prepare for deepep) (#18200) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-05-23 23:43:43 +08:00
Michael Goin
3b17ea26e4 [TPU] Re-enable the Pallas MoE kernel (#18025) 
Signed-off-by: Michael Goin <mgoin64@gmail.com>
 2025-05-20 19:52:27 -07:00
TJian
92540529c0 [Bugfix] [ROCm]: Remove assertion logic when using AITER fused moe in unquantizedMethod to reenable LLama4 BF16 (#18205) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-05-15 09:53:18 -07:00
Mengqing Cao
70f8b96724 [Bugfix] Fix FusedMoEPrepareAndFinalize for cuda-disalike backends (#18178) 
Signed-off-by: Mengqing Cao <cmq0113@163.com>
 2025-05-14 23:16:31 -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
vllmellm
2d912fb66f [FEAT] [ROCm] [V1]: Add AITER biased group topk for DeepSeekV3 (#17955) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-05-13 22:03:47 -07:00
youkaichao
6266c57bae [core][distributed] add ep group and all2all interface (#18077) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-05-14 10:46:49 +08:00
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
Michael Goin
ea6ae8cb45 [Bugfix] Fix marlin moe fallback logic for llama4 (#18042) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-05-13 07:53:28 +00:00
Pavani Majety
0c0fdae84f [Hardware/NVIDIA/Kernel] Enable nvidia/DeepSeek-R1-FP4 Model (#16362) 2025-05-09 16:24:41 -07:00
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
Charlie Fu
ed2462030f [Bugfix] Fix moe weight losing all extra attrs after process_weights_after_loading. (#16854) 
Signed-off-by: charlifu <charlifu@amd.com>
 2025-04-28 21:05:07 +00:00
Lucas Wilkinson
7eb4255628 [BugFix] Accuracy fix for llama4 int4 - improperly casted scales (#16801) 
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
 2025-04-17 22:13:29 -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
c70cf0fe06 [Kernel] Use moe_wna16 kernel for compressed tensors wna16 moe models (#16038) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-04-10 15:08:47 +08:00
zxfan-cpu
ad971af8c7 [Bugfix] fix use-ep bug to enable ep by dp/tp size > 1 (#16161) 2025-04-07 20:48:47 -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
liuzhenwei
0812d8dd41 [Hardware][Gaudi][BugFix] fix arguments of hpu fused moe (#15945) 
Signed-off-by: zhenwei <zhenweiliu@habana.ai>
 2025-04-04 09:38:55 -07:00
Roger Wang
0e00d40e4f [V1][Bugfix] Fix typo in MoE TPU checking (#15927) 
Signed-off-by: Roger Wang <ywang@roblox.com>
 2025-04-01 23:46:42 -07:00
Alexander Matveev
7e4e709b43 [V1] TPU - Fix fused MOE (#15834) 
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
 2025-03-31 22:58:07 -07:00
Robert Shaw
43ed4143c4 [Quantization] Fp8 Channelwise Dynamic Per Token GroupedGEMM (#15587) 
Signed-off-by: ElizaWszola <eliza@neuralmagic.com>
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Co-authored-by: ElizaWszola <eliza@neuralmagic.com>
Co-authored-by: Lucas Wilkinson <wilkinson.lucas@gmail.com>
Co-authored-by: ElizaWszola <ewszola@redhat.com>
 2025-03-27 06:47:25 +00:00
Robert Shaw
e1e0fd7543 [TPU] Avoid Triton Import (#15589) 
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
 2025-03-27 06:43:02 +00:00
Mengqing Cao
fb22be5817 [moe][quant] add weight name case for offset (#15515) 
Signed-off-by: Mengqing Cao <cmq0113@163.com>
 2025-03-27 04:50:29 +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
liuzhenwei
5eeadc2642 [Hardware][Gaudi][Feature] Enable Dynamic MoE for Mixtral (#12303) 
Signed-off-by: zhenwei <zhenweiliu@habana.ai>
 2025-03-24 09:48:40 -07:00
Thien Tran
95d680b862 [Bugfix][IPEX] Add VLLM_CPU_MOE_PREPACK to allow disabling MoE prepack when CPU does not support it (#14681) 
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
 2025-03-13 20:43:18 -07:00
Li, Jiang
ff47aab056 [CPU] Upgrade CPU backend to torch-2.6 (#13381) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
 2025-03-12 10:41:13 +00:00
Tyler Michael Smith
958adce478 [Bugfix] Fix use_direct_call condition in FusedMoE layer for (#14382) 
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2025-03-06 14:17:21 -08:00
Tyler Michael Smith
cc2f9b32c8 [Distributed] Add enable_expert_parallel arg (#14305) 
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2025-03-06 18:54:45 +00:00