iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
11,384 Commits 3 Branches 0 Tags
5bdd15527770ef39cc4c3cdca008fb4f9cf8a15f
Commit Graph
171 Commits
Author SHA1 Message Date
Alexander Matveev e5c78956c0 [Bugfix] Fix incorrect use of hidden_states for shared_experts due to do_naive_dispatch_combine (#28740) 
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
 2025-11-14 14:13:46 -08:00
Alexander Matveev 69d0e90313 [MoE][Kernel][Perf] Improve Shared Expert Stream Overlap (#28406) 
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
 2025-11-12 23:37:24 +00:00
PerryZhang01andPerry Zhang a1e7fa362a [EPLB][ROCm]: support EPBL for ROCm backend (#27731) 
Signed-off-by: Perry Zhang <perzhang@amd.com>
Co-authored-by: Perry Zhang <perzhang@amd.com>
 2025-11-12 18:16:35 +00:00
Michael Goin e5f599d4d1 [Bugfix] Disable shared expert overlap if Marlin MoE is used (#28410) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-11-11 23:16:12 +00:00
bnellnm a1448b4b69 [Kernels] Split up fused_moe/layer.py, isolate more modular kernel code (#28064) 2025-11-11 07:29:02 -07:00
Robert ShawandVadim Gimpelson e605e8e323 [Bugfix] Fix Stream Sync for Shared Expert Overlap (#28430) 
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Co-authored-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
 2025-11-11 05:59:08 +00:00
Ilya MarkovLuka GovedičLuka GovedičRobert Shaw
 		d17ecc6b19 [PERF] Allreduce fusion. Support torch native matching. Tuning of the thresholds (#24248) 
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
 2025-11-10 18:33:11 -05:00
jiahanc 34553b9d27 [Performance] Support FP8 flashinfer TRTLLM MOE on Qwen3 and Qwen-3next (#27492) 
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
 2025-11-10 12:34:57 -05:00
vllmellmandLuka Govedič f080a83511 [RFC][ROCm][AITER] Keep all AITER kernels in _aiter_ops class like _custom_ops and _ipex_ops (#24490) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
 2025-11-10 08:20:53 -08:00
Kunshang Ji 1aaecda078 [XPU] Enable Expert parallel for MoE models (#28263) 
Signed-off-by: Yan Ma <yan.ma@intel.com>
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
 2025-11-08 00:33:11 +00:00
Wentao Ye d71af5f502 [Feature] Enable TP + EP shared_experts overlap with router, 3.7% E2E performance improvement (#28164) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-11-05 17:21:08 -08:00
Frost Mitchell 6e97eccf5d [XPU] Enable custom routing functions in IPEX for Llama4 (#28004) 
Signed-off-by: frost-intel <frost.mitchell@intel.com>
 2025-11-05 13:39:57 +00:00
bnellnm 938772af03 [Kernels] Isolate modular kernel code from FusedMoEMethodBase subclasses. (#27123) 2025-11-04 21:59:45 +08:00
Tyler Michael Smith 3758757377 [Bugfix] Fix MoE Routing Simulation (#28002) 
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
 2025-11-03 22:26:49 +00:00
Jee Jee Li bc4486d609 [Kernel] Enable FusedMoEModularKernel support bias (#27754) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-11-01 02:05:12 +00:00
Wentao Ye fcb1d570bb [Bug] Fix DeepEP low latency assert self.batched_router_logits.size(-1) == full_router_logits.size(-1) Bug (#27682) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-29 14:50:39 -04:00
Wentao YeandCyrus Leung 0484b64248 [Bug] Fix shape issue for eplb expert weights (#27589) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2025-10-28 20:44:05 +08:00
Varun Sundar RabindranathandVarun Sundar Rabindranath 5d3be3ba4c [Bugfix][LoRA][FusedMoE] Select MxFP4 Backend based on LoRA Enablement (#27487) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-10-27 07:32:50 -07:00
Yeshwanth N 71b1c8b667 [Chore]:Extract math and argparse utilities to separate modules (#27188) 
Signed-off-by: Yeshwanth Surya <yeshsurya@gmail.com>
Signed-off-by: Yeshwanth N <yeshsurya@gmail.com>
Signed-off-by: yeshsurya <yeshsurya@gmail.com>
 2025-10-26 04:03:32 -07:00
Wentao Ye 52efc34ebf [Log] Optimize Startup Log (#26740) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-24 19:27:04 -04:00
Alexander Matveev 9ef3d5b875 [Bugfix] Fix dp_chunking enablement logic in FusedMoE layer (#27220) 
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
 2025-10-24 00:03:14 +08:00
tomeras91 61089465a6 [Model] Add MoE support for NemotronH (#25863) 
Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>
 2025-10-23 10:27:23 +00:00
dongbo910220Wentao YeCyrus Leung
 		3ae082c373 [Chore] Separate out optional dependency checks from vllm.utils (#27207) 
Signed-off-by: dongbo910220 <1275604947@qq.com>
Signed-off-by: dongbo910220 <32610838+dongbo910220@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2025-10-22 10:44:21 -04:00
Alexander Matveev 344a0017c0 [Performance] Dual stream execution of "shared_experts" and "selected_experts" inside FusedMoE (#26440) 
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
 2025-10-21 21:38:29 +00:00
Shu WangandMichael Goin f95da13c3d [ModelOpt] Load w13/w2_input_scale for all experts, nvfp4 (#26135) 
Signed-off-by: Shu Wang <shuw@nvidia.com>
Signed-off-by: Shu Wang. <shuw@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2025-10-21 01:50:31 -04:00
Isotr0py 6ac5e06f7c [Chore] Clean up pytorch helper functions in vllm.utils (#26908) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: isotr0py <2037008807@qq.com>
 2025-10-18 09:48:22 -07:00
Varun Sundar RabindranathandVarun Sundar Rabindranath fb0571b077 [GPTOSS][DP/EP][Marlin] Enable GPTOSS Batched DP/EP using Marlin kernels (#25997) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-10-16 12:53:11 -07:00
kliuaevalarLipTJian
 		1317034379 [ROCm][FEAT] Fuse DeepSeek shared experts into AITER fused_moe ops (#24097) 
Signed-off-by: chenjun <junchen2@amd.com>
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
Co-authored-by: valarLip <103567126+valarLip@users.noreply.github.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
 2025-10-16 10:41:34 +08:00
Harry Mellor 8fcaaf6a16 Update Optional[x] -> x | None and Union[x, y] to x | y (#26633) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-12 09:51:31 -07:00
bnellnm da364615fc [Kernels] Modular kernel refactor (#24812) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2025-10-08 17:51:52 -04:00
Benjamin Chislett 2161efe978 [Bugfix] Allow skipping MoE in NVFP4 (fix for MTP) (#25987) 
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
 2025-10-06 16:16:30 -04:00
Harry Mellor b893d661b1 Fix per file ruff ignores related to simplification (#26259) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-05 20:31:53 +00:00
Harry Mellor 4e256cadc2 Remove all references to yapf as it's no longer used (#26251) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-05 09:18:11 -07:00
Harry Mellor d6953beb91 Convert formatting to use ruff instead of yapf + isort (#26247) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-05 07:06:22 -07:00
Harry Mellor 10d765482d FusedMoE support for the Transformers backend (#22650) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-02 23:12:15 -07:00
Matthew Bonanni 13cdc02173 Fix MTP with deepep_low_latency (#25904) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2025-10-02 21:29:49 +00:00
Tyler Michael Smith a5354b3ed2 [Bugfix][WideEP] Apply TP Attn + EP MoE fix to other models (#24982) 
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
 2025-09-27 14:22:28 +00:00
Sage MooreandRobert Shaw dfb9af2014 [Bugfix] Fix Shared Expert/Zero expert code in FusedMoE.process_chunk (#25698) 
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
 2025-09-26 01:25:28 -07:00
XuruiYangandyangxurui 845adb3ec6 [Model] Add LongCat-Flash (#23991) 
Signed-off-by: yangxurui <yangxurui@meituan.com>
Co-authored-by: yangxurui <yangxurui@meituan.com>
 2025-09-24 21:53:40 -07:00
Duncan Moss 6160ba4151 feat: BF16 FlashInfer Fused Cutlass MOE for Hopper and Blackwell Expert Parallel (#25503) 
Signed-off-by: Duncan Moss <djm.moss@gmail.com>
 2025-09-24 18:50:04 -04:00
Harry Mellor 8c853050e7 [Docs] Enable fail_on_warning for the docs build in CI (#25580) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-09-24 19:30:33 +00:00
Nikhil Gupta 359d293006 [fix]: add Arm 4bit fused moe support (#23809) 
Signed-off-by: Nikhil Gupta <nikhil.gupta2@arm.com>
 2025-09-24 01:32:22 +00:00
Michael Goin 7361ab379f Remove redundant mutates_args and dispatch_key for direct_register_custom_op (#25512) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-09-23 22:48:40 +00:00
Joelandyoukaichao 61d1b35561 [BugFix] Register expert_map as named buffer for wake_up and sleep (#25458) 
Signed-off-by: wuxibin <wuxibin@bytedance.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
 2025-09-23 21:49:13 +08:00
Varun Sundar RabindranathandVarun Sundar Rabindranath e8db44f883 [DP/EP][GPTOSS] Use triton matmul-ogs kernels for GPTOSS DP/EP (#24588) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-09-22 21:01:09 -07:00
Bowen Wanggemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>Tyler Michael Smith
 		06a41334c7 [EPLB] Reduce EPLB Inference Overhead (#24573) 
Signed-off-by: Bowen Wang <abmfy@icloud.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2025-09-22 16:31:05 +00:00
YiwenC 9d8a2d86d2 [EPLB] Add EPLB support for hunyuan_v1 (#23078) 2025-09-18 04:51:35 +00:00
bnellnm 5963b98b46 [Kernel] Delegate construction of FusedMoEQuantConfig to FusedMoEMethodBase subclasses (#22537) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2025-09-17 17:43:31 -06:00
Sage MooreLucas WilkinsonLucas Wilkinsonyewentao256Lucas WilkinsonRobert Shaw
 		567939953b [Core/DBO][1/N] Add Dual-Batch Overlap mechanism to VLLM (#23693) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
 2025-09-16 12:21:48 -04:00
Chen Brucelemon412Harry Mellor
 		7ea5c73ad7 [Feat][EPLB] A novel static EPLB placement strategy for MoE models. (#23745) 
Signed-off-by: bruceszchen <bruceszchen@tencent.com>
Signed-off-by: Chen Bruce <bruceszchen@tencent.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Chen Bruce <cszwwdz@vip.qq.com>
Co-authored-by: lemon412 <lemon412@foxmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-09-16 10:55:16 +00:00