 Richard Zou
|
e82fbeec7b
|
[torch.compile] Undo the fast_moe_cold_start hack in torch>=2.11 (#35475)
Signed-off-by: Richard Zou <zou3519@gmail.com>
|
2026-03-01 21:44:22 +00:00 |
|
|
|
dea268336f
|
[1/N] Elastic EP Milestone 2 (#34861)
Signed-off-by: Yongji Wu <wuyongji317@gmail.com>
Signed-off-by: Itay Alroy <ialroy@nvidia.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: Ron Tourgeman <rtourgeman@nvidia.com>
Co-authored-by: Yongji Wu <wuyongji317@gmail.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Ron Tourgeman <rtourgeman@nvidia.com>
|
2026-02-28 04:46:42 +00:00 |
|
|
Chengyi NieandChengyi Nie
|
a572baff5e
|
[Model Performance] Add Qwen3MoE tuned MoE configs for H200 (#35457)
Signed-off-by: Chengyi Nie <cnie@roblox.com>
Co-authored-by: Chengyi Nie <cnie@roblox.com>
|
2026-02-27 13:51:14 +08:00 |
|
|
roikoren755
|
38c498b8e3
|
[Performance] Cublas Bf16 Gate with Fp32 Output (#35121)
Signed-off-by: Roi Koren <roik@nvidia.com>
|
2026-02-26 16:51:28 -08:00 |
|
|
Aleksandr MalyshevandAleksandr Malyshev
|
01923eec70
|
[ROCm][Quantization] GPT OSS Upstream MoE wmxfp4_afp8 with static scales (#30357)
Signed-off-by: Aleksandr Malyshev <maleksan@amd.com>
Co-authored-by: Aleksandr Malyshev <maleksan@amd.com>
|
2026-02-26 16:50:16 -06:00 |
|
|
Tyler Michael SmithandClaude Opus 4.6
|
eb19955c37
|
[WideEP] Remove pplx all2all backend (#33724)
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-02-26 14:30:10 -08:00 |
|
|
Li-Yongwen
|
c6ca51598a
|
[Bugfix] fix device_name for routing replay (#34336)
Signed-off-by: liyongwen <1310439159@qq.com>
|
2026-02-26 12:18:38 +00:00 |
|
|
Michael GoinandRobert Shaw
|
de527e1cec
|
[UX] Add --moe-backend arg for explicit kernel selection (#33807)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-02-25 17:44:44 -08:00 |
|
|
Yongye Zhu
|
1976356ee6
|
[MoE Refactor] MXFP4 Cutlass Experts to MK (#34542)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-02-25 17:32:39 -08:00 |
|
|
|
c97234c08b
|
fix(mxfp4): Disable monolithic path for TRITON backend with EP (#34270)
Signed-off-by: Elizabeth Thomas <email2eliza@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-02-25 13:33:42 -08:00 |
|
|
yugong333andMichael Goin
|
576fe50333
|
Adding Nemotron fp8 Triton MoE Config (#34674)
Signed-off-by: Yu Gong <yu3.gong@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-02-24 15:56:38 -08:00 |
|
|
Michael GoinandRobert Shaw
|
22a97e6613
|
[Perf] Improve default triton fused moe configs (#34846)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-02-23 16:01:28 -08:00 |
|
|
Wentao Ye
|
7f40e9e516
|
[Refactor] Remove dead private func _fp8_perm and _extract_mask_for_item (#35068)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-02-23 05:05:20 -08:00 |
|
|
|
b7892a3bef
|
[Model] Add NVFP4 quantization support for Step3.5-Flash (#34478)
Signed-off-by: tacos8me <ian@cloudhabit.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-02-22 12:30:46 -07:00 |
|
|
Rohan Potdar
|
ded333fb9b
|
[ROCm][Bugfix]: Only save unpadded sizes for shared_experts in MoERunner to fix rmsnorm pad fusion (#34636)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
|
2026-02-20 19:56:16 -08:00 |
|
|
|
81bfc21a6a
|
[Model Bash]: Improve FP8 Oracle for Config Specific Kernel Selection (#34260)
Signed-off-by: Elizabeth Thomas <email2eliza@gmail.com>
Signed-off-by: Robert Shaw <robertgshaw2-redhat@h100-02.nemg-001.lab.rdu2.dc.redhat.com>
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Co-authored-by: Robert Shaw <robertgshaw2-redhat@h100-02.nemg-001.lab.rdu2.dc.redhat.com>
Co-authored-by: Robert Shaw <robertgshaw2@gmail.com>
|
2026-02-19 21:29:08 -08:00 |
|
|
Michael Goin
|
f72061a19a
|
[UX] More descriptive reasons in is_supported_config for MoE (#34908)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-02-19 15:20:52 -08:00 |
|
|
Robert ShawandRobert Shaw
|
4685a630a2
|
[Model Bash][DeepSeekR1] Remove Shared Expert Clone (#34344)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
|
2026-02-19 07:56:14 -08:00 |
|
|
Manrique Vargas
|
ad5aa6bd9f
|
fix(docs): fix typos in comments and docstrings (#34836)
Signed-off-by: machov <mv1742@nyu.edu>
|
2026-02-18 23:17:41 -08:00 |
|
|
Yongye ZhuandRobert Shaw
|
40da9625a1
|
[MoE Refactor] Convert mxfp4 marlin into modular kernel format (#34588)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-02-18 14:37:14 -08:00 |
|
|
|
847a57cd12
|
[Bugfix][MoE Kernel] Fix incorrect routing selection for models without expert groups (e.g., MiniMax-M2.1) (#34673)
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-02-18 13:03:24 -08:00 |
|
|
Jaden Mathias
|
0e60c925cf
|
[Bugfix] Remove assert causing hipErrorStreamCaptureUnsupported (#34455)
Signed-off-by: Jaden Mathias <jaden.mathias@amd.com>
|
2026-02-18 18:54:54 +00:00 |
|
|
Marek Michalowski
|
e89a91d927
|
[Bugfix] fix activation in cpu_fused_moe_torch call (#34696)
Signed-off-by: Marek Michalowski <marek.michalowski@arm.com>
|
2026-02-17 23:39:46 -08:00 |
|
|
haosdentandMichael Goin
|
b68fd899d1
|
[Bugfix] Fix fused MoE int32 overflow in stride*offset without perf regression (#34507)
Signed-off-by: haosdent <haosdent@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-02-16 17:58:49 -08:00 |
|
|
roikoren755
|
3b30e61507
|
[NemotronH] Do not force router to run in fp32 (#34582)
Signed-off-by: Roi Koren <roik@nvidia.com>
|
2026-02-16 10:15:32 -08:00 |
|
|
bnellnm
|
5bff999d12
|
[Bugfix] Add method to swap quant_method on FusedMoE to fix LoRA issues (#34453)
Signed-off-by: Bill Nell <bnell@redhat.com>
|
2026-02-15 20:10:50 -08:00 |
|
|
haosdent
|
79f3fab05a
|
[Bugfix] Handle num_expert_group=None in flashinfer block-scale FP8 MoE (#34494)
Signed-off-by: haosdent <haosdent@gmail.com>
|
2026-02-14 23:25:46 -08:00 |
|
|
Michael Goin
|
bfaa559305
|
Revert "[Bugfix] Fix fused MoE IMA (sans chunking) by using int64 for strides" (#34530)
|
2026-02-13 10:35:29 -08:00 |
|
|
Matthias GehreandTJian
|
934acddef9
|
[Perf] fused_moe: add int4_w4a16 benchmark support and tuning config (#34130)
Signed-off-by: Matthias Gehre <matthias.gehre@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-02-13 00:14:27 -08:00 |
|
|
bnellnm
|
04ea31baab
|
[Bugfix] Remove assert that's no longer valid (#34443)
Signed-off-by: Bill Nell <bnell@redhat.com>
|
2026-02-12 18:18:15 -08:00 |
|
|
amitz-nv
|
f120bd42d3
|
[Kernel] Support Flashinfer trtllm fused MoE non gated FP8 & NVFP4 (#33506)
Signed-off-by: amitz-nv <203509407+amitz-nv@users.noreply.github.com>
|
2026-02-12 13:06:58 -08:00 |
|
|
danisereb
|
dea63512bb
|
Add config file for fused MoE for Nemotron (TP4, B200) (#34411)
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
|
2026-02-12 06:09:55 -08:00 |
|
|
Lucas WilkinsonandBill Nell
|
136b0bfa59
|
[BugFix] Fix DP chunking (#34379)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Bill Nell <bnell@redhat.com>
|
2026-02-12 06:44:03 +00:00 |
|
|
Michael Goin
|
ff1f83b056
|
[Refactor] Replace activation: str with MoEActivation enum (#33843)
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
|
2026-02-11 17:29:32 -08:00 |
|
|
bnellnm
|
31d992d215
|
[Bugfix] Fix some issues with MoERunner PR #32344 (#34371)
Signed-off-by: Bill Nell <bnell@redhat.com>
|
2026-02-11 14:33:14 -08:00 |
|
|
LindaandPavani Majety
|
275e0d2a99
|
[NVIDIA][test] Tests for flashinfer TRTLLM BF16 MoE (#33715)
Signed-off-by: Linda-Stadter <57756729+Linda-Stadter@users.noreply.github.com>
Co-authored-by: Pavani Majety <pmajety@nvidia.com>
|
2026-02-11 12:38:11 +00:00 |
|
|
Li, Jiang
|
05339a7b20
|
[Bugfix][CPU] Fix llama4 inference on CPU (#34321)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-02-11 19:07:23 +08:00 |
|
|
Harry Mellor
|
40b8f55358
|
[Docs] Reduce time spent generating API docs (#34255)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-02-11 02:56:02 -08:00 |
|
|
Tyler Michael SmithandClaude Opus 4.6
|
d7982daff5
|
[Bugfix] Fix fused MoE IMA (sans chunking) by using int64 for strides (#34279)
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-02-11 05:15:52 +00:00 |
|
|
zofia
|
b482f71e9f
|
[XPU][7/N] enable xpu fp8 moe (#34202)
Signed-off-by: Zhu, Zufang <zufang.zhu@intel.com>
|
2026-02-11 03:33:59 +00:00 |
|
|
bnellnm
|
d1481ba783
|
[MoE Refactor] Introduce MoERunner abstraction and move execution logic from FusedMoE to DefaultMoERunner (#32344)
Signed-off-by: Bill Nell <bnell@redhat.com>
|
2026-02-10 19:51:07 -05:00 |
|
|
|
b129136c7a
|
[ROCm][Quantization] GPT_OSS in amd-quark format model loading and emulations (#29008)
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-02-10 10:08:05 -05:00 |
|
|
Gregory Shtrasberg
|
c60f8e3b49
|
[Bugfix][ROCm][GPT-OSS] Use old triton_kernels implementation on ROCm if the new API is not available (#34153)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
|
2026-02-09 17:38:54 -06:00 |
|
|
TomerBN-NvidiaandCursor
|
995bbf38f1
|
[Bugfix] Fix shared expert input for latent MoE in EP+DP (Nemotron-H) (#34087)
Signed-off-by: Tomer Natan <tbarnatan@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-02-09 16:44:18 +00:00 |
|
|
Andrey Talman
|
f97ca67176
|
[Release 2.10] Update to Torch 2.10 - final release (#30525)
|
2026-02-08 13:51:09 -08:00 |
|
|
danisereb
|
084aa19f02
|
Add support for ModelOpt MXFP8 dense models (#33786)
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
|
2026-02-08 11:16:48 -08:00 |
|
|
navmarri14
|
1ecfabe525
|
glm 4.6 fused tuned inference config for B200 (#32958)
|
2026-02-08 18:55:47 +00:00 |
|
|
TomerBN-NvidiaandTomer Natan
|
a263aa6140
|
[BugFix] Change support no act and mul for marlin (#34088)
Signed-off-by: Tomer Natan <tbarnatan@computelab-frontend-8.nvidia.com>
Co-authored-by: Tomer Natan <tbarnatan@computelab-frontend-8.nvidia.com>
|
2026-02-08 17:18:22 +00:00 |
|
|
lukec
|
15a0b9e570
|
Fix spelling errors (#33978)
|
2026-02-06 23:58:50 -08:00 |
|
|
|
207c3a0c20
|
Fix RoutingMethodType logic (#33919)
Signed-off-by: Dimitrios Bariamis <12195802+dbari@users.noreply.github.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Dimitrios Bariamis <12195802+dbari@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2026-02-06 14:03:34 -08:00 |
|