+5
e126687a9a
[Model] Support Qwen3.8-Flash-Next ( #53896 )
...
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com >
Signed-off-by: andyluo7 <andy.luo@amd.com >
Signed-off-by: lishunyang12 <lishunyang03@gmail.com >
Signed-off-by: Harry Huang <huanghaoyan.hhy@alibaba-inc.com >
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg >
Signed-off-by: Isotr0py <Isotr0py@outlook.com >
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com >
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai >
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com >
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com >
Co-authored-by: KungYork <firelikest@163.com >
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg >
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai >
Co-authored-by: andyluo7 <43718156+andyluo7@users.noreply.github.com >
Co-authored-by: Isotr0py <mozf@inferact.ai >
Co-authored-by: andyluo7 <andy.luo@amd.com >
Co-authored-by: OpenAI Codex <noreply@openai.com >
Co-authored-by: lishunyang12 <lishunyang03@gmail.com >
Co-authored-by: Vadim Gimpelson <156319763+vadiklyutiy@users.noreply.github.com >
Co-authored-by: Isotr0py <Isotr0py@outlook.com >
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com >
Co-authored-by: Claude Opus 5 <noreply@anthropic.com >
Co-authored-by: OpenAI Codex <codex@openai.com >
2026-08-31 05:57:56 +00:00
Shenglei Fu and Claude Fable 5
129087ddab
[Perf] Reuse topk SparseMatrix routing metadata in GPT-OSS MoE forward ( #45457 )
...
Signed-off-by: Shenglei Fu <sfu@confluent.io >
Signed-off-by: Shenglei Fu <117230642+ShengleiFu@users.noreply.github.com >
Co-authored-by: Claude Fable 5 <noreply@anthropic.com >
2026-08-29 12:14:39 -04:00
ca29cd48ba
[Quantization][Humming] Support MXFP4 weight + block-FP8 activation for MoE ( #51332 )
...
Signed-off-by: Elvir Crncevic <elvircrn@gmail.com >
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com >
Signed-off-by: Elvir Crnčević <elvircrn@gmail.com >
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com >
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-08-25 10:21:00 -04:00
Andreas Karatzas
a0af854f5d
[ROCm][CI] Stabilize MI355 FlyDSL MoE accuracy test ( #53024 )
...
Signed-off-by: Andreas Karatzas <akaratza@amd.com >
2026-08-21 13:17:18 -07:00
Andreas Karatzas
88eb946cb1
[ROCm][CI] Stabilize MI355 FusedMoE test group ( #53025 )
...
Signed-off-by: Andreas Karatzas <akaratza@amd.com >
2026-08-21 13:15:25 -07:00
vllm-agent and vllm-ci-failure-analyzer
ba53da60bb
Revert "[Bugfix][MoE] Tune FlashInfer experts to scheduler token limit" ( #52989 ) ( #53186 )
...
Co-authored-by: vllm-ci-failure-analyzer <kevin@inferact.ai >
2026-08-21 12:39:28 -06:00
Luke Alonso and mgoin
2740c817ff
[Kernel] Add b12x FP4 MoE backend ( #52018 )
...
Signed-off-by: Luke Alonso <lalonso@gmail.com >
Signed-off-by: mgoin <mgoin64@gmail.com >
Signed-off-by: Misha Goin <mgoin64@gmail.com >
Co-authored-by: mgoin <mgoin64@gmail.com >
2026-08-21 08:04:36 -07:00
Wei Zhao and OpenAI Codex
f8e0602713
Support kimi k3 nvfp4 checkpoint ( #53132 )
...
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com >
Co-authored-by: OpenAI Codex <codex@openai.com >
2026-08-21 05:59:44 +00:00
Misha Goin and OpenAI Codex
bfb6c13499
[Bugfix][MoE] Tune FlashInfer experts to scheduler token limit ( #52989 )
...
Signed-off-by: mgoin <mgoin64@gmail.com >
Co-authored-by: OpenAI Codex <codex@openai.com >
2026-08-20 16:26:24 -04:00
pmanczak
44cf3f0466
[XPU][Tests] Make tests device-agnostic ( #51968 )
...
Signed-off-by: pmanczak <pawel.manczak@intel.com >
2026-08-20 02:25:41 -07:00
Sage Moore
5bf0dbd6fd
[Bugfix] vLLM crashes at startup when DeepEP v2 is used with --enforce-eager wiht TRTLLM Bf16 ( #51824 )
2026-08-19 20:18:47 -04:00
Andreas Karatzas
480d4f0d15
[ROCm][CI] Enable modular OAI Triton MoE tests ( #46434 )
...
Signed-off-by: Andreas Karatzas <akaratza@amd.com >
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com >
2026-08-19 13:46:12 -05:00
xuebwang-amd
c676232313
[Bugfix][Quantization] Fix OCP MX MoE emulation silently skipping mxfp6 activation QDQ ( #52704 )
...
Signed-off-by: xuebwang-amd <xuebwang@amd.com >
2026-08-19 11:29:29 -05:00
akii96
583a00257d
[ROCm] [Bugfix] Fix Triton fused shared expert alignment ( #51632 )
...
Signed-off-by: Aakif Nawaz <aakif.nawaz@amd.com >
2026-08-20 00:14:52 +08:00
Andreas Karatzas
17dbd42930
[ROCm] Add UE8M0 scale packing for Triton silu_mul_quant ( #37835 )
...
Signed-off-by: Andreas Karatzas <akaratza@amd.com >
2026-08-19 10:20:05 -05:00
Andreas Karatzas
160f7f0840
[ROCm][CI] Extended Fused MoE and FP8 MoE test support ( #41100 )
...
Signed-off-by: Andreas Karatzas <akaratza@amd.com >
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com >
2026-08-19 10:19:42 -05:00
Bo Li and mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
c296851a7d
[MoE] Refine FlashInfer one-sided All2All integration ( #51924 )
...
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-08-18 00:18:14 +00:00
Micah Williamson
8878ebd8fd
[ROCm][CI] Expand AITER W4A4 MoE Coverage ( #52647 )
...
Signed-off-by: Micah Williamson <micah.williamson@amd.com >
2026-08-17 15:46:22 -05:00
Gabriel Wu
97388c44f9
[Bugfix] Make DSV4 sparse MLA work end-to-end for plain decode, MTP, and DSpark ( #51538 )
2026-08-15 07:01:32 -07:00
Guanxin Li and Claude Opus 5
925ea7e60f
[CI][Test] Seed the DeepEP v2 MoE workers, not just the parent ( #50589 )
...
Signed-off-by: Guanxin Li <guanxinl@nvidia.com >
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com >
2026-08-14 16:01:24 -04:00
ccaadaro and Li, Jiang <jiang1.li@intel.com>
bda4c3e8ee
[CPU] Fold the MXFP4 block scale in 2 instructions instead of 4 ( #51583 )
...
Signed-off-by: ccaadaro <ccanadar@unex.es >
Co-authored-by: Li, Jiang <jiang1.li@intel.com >
2026-08-14 08:19:21 +00:00
61826c1c6f
[Hardware][Power] Unqualized MoE Backend for Power (VSX) ( #51624 )
...
Signed-off-by: Akash kaothalkar <akash.kaothalkar@ibm.com >
Co-authored-by: Akash kaothalkar <akash.kaothalkar@ibm.com >
Co-authored-by: Antigravity <antigravity@google.com >
2026-08-13 10:56:09 +08:00
stefankoncarevic
d20a031d33
[Bugfix][ROCm][MoE] Update AITER MXFP4 W4A16 tests to the renamed expert_mask ( #51980 )
...
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com >
2026-08-12 17:45:45 +00:00
Andreas Karatzas and mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
36f4630d89
[Bugfix][MoE] Fix fused block-scale orientation ( #50727 )
...
Signed-off-by: Andreas Karatzas <akaratza@amd.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-08-11 16:05:38 -04:00
pmanczak and Kunshang Ji
5b5eae2394
[Misc] Enable test_silu_mul_fp8_quant_deep_gemm on XPU ( #49444 )
...
Signed-off-by: pmanczak <pawel.manczak@intel.com >
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com >
2026-08-11 23:19:14 +08:00
Fangzhou Ai
1044d19998
[ROCm][DSV4] Preserve native MXFP4 TP8 shard allocation ( #51473 )
...
Signed-off-by: Fangzhou Ai <fangzhou.ai@amd.com >
2026-08-10 23:57:27 -07:00
Priyansh Jain and Andreas Karatzas
2acb055ed7
[CPU][Zen] Route BF16 MoE inference through zentorch on AMD ( #44201 )
...
Co-authored-by: Andreas Karatzas <akaratza@amd.com >
2026-08-10 23:20:05 -07:00
pmanczak
ec21f61d82
[Misc] Enable test_fused_moe_wn16 on XPU ( #51672 )
...
Signed-off-by: pmanczak <pawel.manczak@intel.com >
2026-08-10 21:57:02 +08:00
Isotr0py
073c510c91
[Migration] Migrate bitsandbytes support to OOT plugin ( #43529 )
...
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn >
Signed-off-by: Isotr0py <Isotr0py@outlook.com >
2026-08-09 10:27:31 +08:00
Tianmu Li
700d39b558
[CPU] Optimize routed FP8/MXFP4 MoE GEMM dispatch ( #50949 )
...
Signed-off-by: Li, Tianmu <tianmu.li@intel.com >
2026-08-08 12:56:14 +08:00
Walter Beller-Morales and Harry Mellor
70456e5e6f
[Bugfix] when loading weights skip empty expert bias if model does not support them ( #50937 )
...
Signed-off-by: walterbm <walter.beller.morales@gmail.com >
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2026-08-07 12:45:52 -07:00
Jinzhen Lin and OpenAI Codex
fcde8e1460
[Refactor] refactor humming linear and moe backends to use explicit layer configs ( #49610 )
...
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com >
Co-authored-by: OpenAI Codex <noreply@openai.com >
2026-08-07 10:03:19 -07:00
Julien Debache
ae934ba8a5
feat: extended EPLB support for Mistral Large 3 and additional MoE backends ( #48355 )
...
Signed-off-by: jdebache <jdebache@nvidia.com >
2026-08-07 05:32:52 -07:00
0de0362ea1
[ROCm][CI] Loosen block-FP8 fused MoE test tolerance for large-K shapes ( #48847 )
...
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com >
Signed-off-by: Andreas Karatzas <akaratza@amd.com >
Co-authored-by: Andreas Karatzas <akaratza@amd.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-08-07 01:19:26 -07:00
e08111211b
[Kernel] Support Nvfp4 Cutedsl Moe Swiglu-oai and Relu2(non-gated) Activation ( #47106 )
...
Signed-off-by: Tiekai Bi <tiekaib@nvidia.com >
Co-authored-by: Claude Opus 5 <noreply@anthropic.com >
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com >
2026-08-06 17:42:45 -07:00
Gabriel Wu and Yongye Zhu
2e35c529b8
[Bugfix][Quantization] Fix MXFP4 conversion for FlashInfer CUTLASS ( #51038 )
...
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com >
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com >
2026-08-05 23:19:22 -07:00
Micah Williamson and Andreas Karatzas
4282fe52d5
[ROCm][CI] Add More AITER quantization/MoE kernel tests ( #49375 )
...
Signed-off-by: Micah Williamson <micah.williamson@amd.com >
Co-authored-by: Andreas Karatzas <akaratza@amd.com >
2026-08-05 21:27:33 +00:00
stefankoncarevic and Andreas Karatzas
65addac701
[ROCm][CI] Keep rocprofiler-sdk out of DeepEP HT MoE test workers ( #51173 )
...
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com >
Co-authored-by: Andreas Karatzas <akaratza@amd.com >
2026-08-05 15:28:41 -05:00
Rohan Potdar and Claude Opus 4.8
c2d8009044
[ROCm] Work around DeepEP teardown SIGSEGV in MoE test harness ( #51174 )
...
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com >
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-08-05 14:44:42 -05:00
Michael Goin and OpenAI Codex
8f158d0ee2
[MoE] Share apply_moe_activation support metadata ( #44359 )
...
Signed-off-by: mgoin <mgoin64@gmail.com >
Co-authored-by: OpenAI Codex <codex@openai.com >
2026-08-05 12:05:47 -07:00
Gabriel Wu and Pavani Majety
08b8613b7b
[Bugfix][Model] Fix MiniMax-M3 NVFP4 inference correctness ( #48929 )
...
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com >
Co-authored-by: Pavani Majety <pmajety@nvidia.com >
2026-08-05 07:25:46 -07:00
aoshen02 and Nick Hill
42ab184ea7
[MRV2] Enable routed-experts capture ( #50721 )
...
Signed-off-by: aoshen02 <aoshen@inferact.ai >
Signed-off-by: Nick Hill <nickhill123@gmail.com >
Co-authored-by: Nick Hill <nickhill123@gmail.com >
2026-08-03 21:00:13 +00:00
Andreas Karatzas
e279f71583
[ROCm][Test] Fix AITER MXFP4 oracle contract ( #50728 )
...
Signed-off-by: Andreas Karatzas <akaratza@amd.com >
2026-08-03 20:53:18 +00:00
0a6446005d
[CPU] Migrate unquantized MoE to the modular-kernel experts structure ( #50133 )
...
Signed-off-by: jiang1.li <jiang1.li@intel.com >
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com >
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com >
Co-authored-by: Fadi Arafeh <fadi.arafeh@arm.com >
2026-08-03 14:55:04 +08:00
Amir Samani
c4a4a42d80
[Bugfix][Test] Fix monolithic routing replay test buffer capacity ( #50640 )
2026-07-31 19:37:39 -07:00
94e9ef0768
[Bugfix] Don't transpose fused MoE quantization scales in RoutedExperts.load_weights ( #50137 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
Co-authored-by: Claude Opus 5 <noreply@anthropic.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-07-31 08:46:52 -07:00
bnellnm and Harry Mellor
6e311c6e20
[MoE Refactor] Rename FusedMoE to FusedMoEFactory ( #44941 )
...
Signed-off-by: Bill Nell <bnell@redhat.com >
Signed-off-by: bnellnm <49004751+bnellnm@users.noreply.github.com >
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2026-07-31 11:28:18 +01:00
Matt and Andreas Karatzas
d91f7af7d0
[Hardware][AMD][Kernel][CI][Bugfix] Fix ROCm DeepEP FP8 max ( #50467 )
...
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com >
Co-authored-by: Andreas Karatzas <akaratza@amd.com >
2026-07-30 21:37:36 -05:00
+1
4f1da84eb5
Enable gfx1250 ROCm architecture ( #46516 )
...
Signed-off-by: Douglas Lehr <Doug.Lehr@amd.com >
Signed-off-by: jpvillam <juan.villamizar@amd.com >
Signed-off-by: Daniel <danichan@amd.com >
Signed-off-by: Jaden Mathias <jaden.mathias@amd.com >
Signed-off-by: jpvillam <jpvillam@amd.com >
Signed-off-by: Juan Villamizar <100237675+jpvillam-amd@users.noreply.github.com >
Signed-off-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com >
Signed-off-by: Jaden Mathias <Jaden.Mathias@amd.com >
Co-authored-by: Douglas Lehr <Doug.Lehr@amd.com >
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
Co-authored-by: Daniel <danichan@amd.com >
Co-authored-by: Jaden Mathias <jaden.mathias@amd.com >
Co-authored-by: jpvillam <jpvillam@amd.com >
Co-authored-by: root <root@ctheliosr-1b114-f01-2.mnb.dcgpu >
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com >
Co-authored-by: dllehr <douglehr@amd.com >
Co-authored-by: Daniel Chan <Daniel.Chan@amd.com >
Co-authored-by: Andreas Karatzas <akaratza@amd.com >
2026-07-31 01:41:12 +00:00
Wentao Ye
0bff0ce5d3
[Kimi K3 Bug] Fix deepgemm support for kimi k3 ( #50458 )
...
Signed-off-by: yewentao256 <zhyanwentao@126.com >
2026-07-30 20:10:16 -04:00
