|
ddd3855a28
|
[MoE Backend] add HPC-Ops MoE backend (#45924)
Signed-off-by: chengvjiang <chengvjiang@tencent.com>
Co-authored-by: chengvjiang <chengvjiang@tencent.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
|
2026-06-27 11:18:07 +08:00 |
|
|
fxmarty-amd
|
37ce34922f
|
[CI] Fix failing CUDA graph capture in Triton MOE (#46735)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
|
2026-06-26 07:21:20 -07:00 |
|
|
Hongxia YangandClaude Opus 4.8
|
c2507fb293
|
[ROCm] [MoE] [Perf] Shared-expert fusion for bias-routed MoE; enable on MiniMax-M3 mxfp8 model (#46545)
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-06-26 07:05:20 -07:00 |
|
|
TJian
|
8921c4be88
|
[ROCm] [Performance] Optimize aiter moe for DeepSeekV4 (#46122)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2026-06-26 06:43:27 -07:00 |
|
|
qli88andTJian
|
8e394244a5
|
[ROCm]Enable AITER MoE backend for MiniMax-M3-MXFP4 (#46419)
Signed-off-by: Qiang Li <qiang.li2@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-06-26 06:35:35 -07:00 |
|
|
fxmarty-amd
|
552a9dbe59
|
[NVFP4][Emulation] Fuse NVFP4 weight dequantization with compute in triton kernel for w13/w2 MOE MLP linears (#44667)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
|
2026-06-25 19:33:00 -07:00 |
|
|
Mike GandMichael Goin
|
ad28d605e6
|
[Bugfix] Default tie_weights to sharing the weight (fix tied quantized embeddings, e.g. ModelOpt Gemma4) (#45544)
Signed-off-by: Mike G <180722391+mikekg@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-06-25 17:46:28 -07:00 |
|
|
Michael Goin
|
e8e7b592d1
|
[Kernel][MoE] Tune block-FP8 fused MoE for low-batch decode (#46642)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-06-25 12:38:28 -07:00 |
|
|
Qiuyang Yueandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
9bfd878a48
|
[MoE] [MoE Refactor] Add moe kernel oracle abc 37753 (#43461)
Signed-off-by: Qiuyang Yue <yueqiuyang1389@gmail.com>
Signed-off-by: qyYue1389 <yueqiuyang1389@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-25 09:34:03 -04:00 |
|
|
|
710ebaa189
|
[ROCm][Bugfix] Fix chunk alignment when using context parallelism with TRITON_MLA (#46114)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-25 00:07:28 -04:00 |
|
|
Xin Yang
|
1273a8f05a
|
[Kernel] Add swap AB optimization to fused_moe_kernel (#36559)
Signed-off-by: Xin Yang <xyangx@amazon.com>
|
2026-06-25 01:44:30 +00:00 |
|
|
Kaihang Jiang
|
fc7fc421e9
|
[Kernel][MoE] Allow FlashInfer MXINT4 MoE for gated SiLU (#46518)
Signed-off-by: Kaihang Jiang <kaihangj@nvidia.com>
|
2026-06-24 18:32:50 -05:00 |
|
|
Woosuk KwonandClaude
|
d7ab9be775
|
[Bugfix] Support -1 (invalid/non-local) slots in topk_ids for Triton MoE (#46408)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-06-24 13:59:42 -07:00 |
|
|
Woosuk KwonandClaude
|
6a1570711c
|
[Bugfix] Support non-power-of-2 top_k in legacy triton_kernels routing (#46406)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-06-24 13:52:09 -07:00 |
|
|
|
49f2104c53
|
[Feature] Support DCP with FP8 KV cache in MLA decode path (#44044)
Signed-off-by: shivampr <shivampr.dev@gmail.com>
Signed-off-by: Shivam <shivamprasad91@gmail.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-24 19:28:17 +00:00 |
|
|
HDCharlesandClaude Opus 4.6
|
56ca5997ea
|
Humming support for 2/3/5/6/7-bit pack-quantized weight-only inference (#46389)
Signed-off-by: HDCharles <charlesdavidhernandez@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-06-24 13:53:54 -04:00 |
|
|
Fadi Arafeh
|
061043eaca
|
[CPU][Perf] Accelerate unquantized MoE for AArch64 (#46353)
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
|
2026-06-24 14:14:35 +00:00 |
|
|
Woosuk Kwon
|
96de8bb389
|
[MoE] Free unused MXFP4 scales in OAI Triton Backend (#46549)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-06-24 00:06:41 -07:00 |
|
|
Jee Jee Li
|
9d6fdc2901
|
[Kernel] GLM5 Router GEMM (#46385)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-06-23 22:54:50 -07:00 |
|
|
Roberto L. Castro
|
855cd4d787
|
[Perf][DSv4/DSv3.2] Add cluster-cooperative topK kernel for low-latency scenarios (#43008)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
|
2026-06-23 16:11:00 -07:00 |
|
|
Woosuk Kwonandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
0a3e2dbc09
|
[Optimization] Skip DP padding tokens in MoE (#46428)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-23 14:54:46 -07:00 |
|
|
|
0d4d164488
|
[Bugfix] Allow flashinfer_cutlass as a clamped NVFP4 MoE backend (#46492)
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-06-23 12:43:36 -07:00 |
|
|
Mike G
|
0775b882ba
|
[NVFP4 MoE/Deepseek V4] Marlin: wire SwiGLU clamp + allow it for clamped models on non-Blackwell (#45836)
Signed-off-by: Mike G <180722391+mikekg@users.noreply.github.com>
|
2026-06-23 12:21:19 -07:00 |
|
|
Yan Ma
|
acce57d8dd
|
Deprecate old FP8 online MoE quantization class (#44514)
Signed-off-by: Yan Ma <yan.ma@intel.com>
|
2026-06-23 11:53:38 -07:00 |
|
|
Michael GoinandClaude
|
37a682d392
|
[Kernel] Extend Marlin thread-tile padding to MoE (WNA16 + FP8/MXFP8) (#45703)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-06-23 11:45:10 -07:00 |
|
|
fxmarty-amd
|
e368415daa
|
[AMD][OCP MX][CI] Fix tests to not dispatch on UNFUSED_TRITON backend on MI300, improve w_mxfp4_a_fp8 emulation support (#46142)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
|
2026-06-23 14:25:27 -04:00 |
|
|
Willow Lopez
|
f3410b3bb1
|
fix(moe_wna16): access tp_size via moe_config for RoutedExperts compatibility (#45404)
Signed-off-by: Oxygen <1391083091@qq.com>
Signed-off-by: Willow Lopez <100782273+Oxygen56@users.noreply.github.com>
|
2026-06-23 11:46:23 -04:00 |
|
|
Yan Ma
|
547d2c40d7
|
Add weights padding for fp8 per-block online quantization (#44763)
Signed-off-by: Yan Ma <yan.ma@intel.com>
|
2026-06-23 11:08:17 -04:00 |
|
|
Woosuk Kwon
|
04c2a8deac
|
[DeepEP V2] Fill invalid recv_topk_idx with -1 (#46432)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-06-22 21:45:49 -07:00 |
|
|
Mike G
|
56e5797511
|
[Quant] Enable modelopt_mixed on Turing (SM75) (#45375)
Signed-off-by: Mike G <180722391+mikekg@users.noreply.github.com>
|
2026-06-22 19:30:49 -07:00 |
|
|
Michael GoinandClaude Opus 4.8
|
8207ce0850
|
[Bugfix] Fix humming lm_head crash and FusedMoE weight_shape coercion (#46420)
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-06-22 18:19:29 -07:00 |
|
|
|
e48592066e
|
[DeepEP V2] Bound num_max_tokens_per_rank in do_expand=False (#46404)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Roy Wang <jasonailu87@gmail.com>
Co-authored-by: gnovack <novackgm@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-22 18:14:53 -07:00 |
|
|
Bowen BaoandAndreas Karatzas
|
c97e8f99d6
|
[ROCm][Quantization][4/N] refactor quark_moe fp8 w/ oracle (#43721)
Signed-off-by: Bowen Bao <bowenbao@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-06-22 15:58:03 -07:00 |
|
|
ZewenShen-Cohereandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
ca5b24695b
|
Fix static actorder handling for compressed-tensors WNA16 MoE (#41161)
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-22 15:46:46 -07:00 |
|
|
|
c0b2d8f471
|
[Bugfix] FusedMoE: coerce shape-(1,) per-tensor scales to 0-D scalar … (#43362)
Signed-off-by: Varshith <kvarshithgowda@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-06-22 13:26:53 -07:00 |
|
|
|
44d95069e9
|
Enable DeepSeek V4 and GLM-5.1 on SM120 (#43477)
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-06-22 11:54:14 -07:00 |
|
|
Jinzhen Linandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
e4b3da3feb
|
[Quantization][CI] add humming lm-eval test (#43752)
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-22 11:23:55 -07:00 |
|
|
Martin Hickey
|
ccd49f6821
|
[MyPy] Fix mypy for vllm/lora (#41722)
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
|
2026-06-22 10:57:09 -04:00 |
|
|
Liangliang Ma
|
3da4a1b124
|
[XPU] add awq format for INCXPULinear (#43404)
Signed-off-by: Ma, Liangliang <liangliang.ma@intel.com>
|
2026-06-22 22:29:13 +08:00 |
|
|
Yifan Qiao
|
aa4990a9a2
|
[Attention] Re-enable cross-layer KV cache layout for MLA via stride-aware kernels (#45111)
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
|
2026-06-22 06:57:02 -07:00 |
|
|
Tuukka Sarvi
|
89accad2cc
|
[ROCm][DSV4] Disable TileLang MHC dispatch on gfx942 (#45931)
Signed-off-by: Tuukka Sarvi <tuukka.sarvi@amd.com>
|
2026-06-22 09:26:54 +00:00 |
|
|
Athrael SojuandClaude Opus 4.8
|
3c8e49596c
|
[Model] ColQwen3.5: fix retrieval correctness (bias + bidirectional) (#46108)
Signed-off-by: Athrael Soju <athrael.soju@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-06-22 17:25:54 +08:00 |
|
|
Ma Jian
|
9037498c22
|
[DSV4][XPU] Pass gemm1_clamp_limit to XpuFusedMoe (#44517)
Signed-off-by: Ma Jian <jian1.ma@intel.com>
|
2026-06-22 12:57:10 +08:00 |
|
|
fxmarty-amdandAndreas Karatzas
|
485bbe1c6f
|
[CI] Fix missing tp_size attribute on RoutedExperts (#46163)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-06-21 18:46:49 -06:00 |
|
|
Jee Jee Li
|
745bba5ea8
|
[Model]Fix MiniMaxM2ForCausalLM perf regression (#45935)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-06-22 00:28:52 +08:00 |
|
|
Matt
|
a346d589f5
|
[Bugfix] Fix NVFP4/OCP MX MoE emulation (#46254)
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
|
2026-06-20 23:13:10 -05:00 |
|
|
Nick Hill
|
7df3d7dada
|
[Core] Ensure memory is pinned prior to async h2d copy (#45424)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-06-20 20:02:24 -07:00 |
|
|
Jared Wen
|
ab66606993
|
[bugfix]Indexer init skip and MTP TopK share for iteration (#45895)
Signed-off-by: JaredforReal <w13431838023@gmail.com>
|
2026-06-19 09:57:51 +08:00 |
|
|
|
9ea3a4015b
|
[Bugfix] Fix corrupt outputs in MoE FP8 LoRA responses and MoE base model responses when LoRAs are loaded (#42120)
Signed-off-by: Nicholas Edelman <nedelman@nvidia.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-06-18 18:26:09 -07:00 |
|
|
Ting SUNandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
79ca54d221
|
[Bugfix][Quantization] Don't reject fp8_e5m2 KV cache for non-fp8 quantized checkpoints (#45040)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-18 14:18:25 -04:00 |
|