 Lei Wangandxinyuxiao
|
8d32dc603d
|
[Kernel] Support Microsoft Runtime Kernel Lib for our Low Precision Computation - BitBLAS (#6036)
Signed-off-by: xinyuxiao <xinyuxiao2024@gmail.com>
Co-authored-by: xinyuxiao <xinyuxiao2024@gmail.com>
|
2025-04-22 09:01:36 +01:00 |
|
|
Charlie FuandTyler Michael Smith
|
188b7f9b8c
|
[Performance][ROCm] Add skinny gemms for unquantized linear on ROCm (#15830)
Signed-off-by: charlifu <charlifu@amd.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
|
2025-04-21 20:46:22 -07:00 |
|
|
Varun Sundar Rabindranathandvarun sundar rabindranath
|
7b8a2ab76f
|
[Kernel] Add expert_map support to Cutlass FP8 MOE (#16861)
Signed-off-by: varun sundar rabindranath <vsundarr@redhat.com>
Co-authored-by: varun sundar rabindranath <vsundarr@redhat.com>
|
2025-04-21 20:44:32 -07:00 |
|
|
|
5b794cae8d
|
[ROCm] Add aiter tkw1 kernel for Llama4 fp8 (#16727)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: vllmellm <vllm.ellm@embeddedllm.com>
|
2025-04-21 20:42:34 -07:00 |
|
|
Chanh NguyenandChanh Nguyen
|
299ebb62b2
|
[Core] Speed up decode by remove synchronizing operation in sampler (#16436)
Signed-off-by: Chanh Nguyen <cnguyen@linkedin.com>
Co-authored-by: Chanh Nguyen <cnguyen@linkedin.com>
|
2025-04-21 18:18:22 +00:00 |
|
|
Divakar Verma
|
1d4680fad2
|
[rocm][MI300] llama4 maverick fp8 moe config tp8 (#16847)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2025-04-19 06:21:43 +00:00 |
|
|
|
2c1bd848a6
|
[Model][VLM] Add Qwen2.5-Omni model support (thinker only) (#15130)
Signed-off-by: fyabc <suyang.fy@alibaba-inc.com>
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Xiong Wang <wangxiongts@163.com>
|
2025-04-18 23:14:36 -07:00 |
|
|
wang.yuqi
|
3d3ab3689f
|
[New Model]: Snowflake Arctic Embed (Family) (#16649)
|
2025-04-18 08:11:57 -07:00 |
|
|
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 |
|
|
Sijia(Jackson) Chen
|
92edf35826
|
[ROCM] enable aiter fused moe kernel for llama4 bf16 checkpoints (#16674)
|
2025-04-17 11:44:34 -07:00 |
|
|
Ximingwang-09andximing.wxm
|
a018e555fd
|
[Kernel] Add fp8_w8a8 fused MoE kernel tuning configs for DeepSeek V3/R1 on NVIDIA H20 (#16753)
Signed-off-by: ximing.wxm <ximing.wxm@antgroup.com>
Co-authored-by: ximing.wxm <ximing.wxm@antgroup.com>
|
2025-04-18 00:01:30 +08:00 |
|
|
Dipika Sikka
|
54a66e5fee
|
[Misc] Update compressed-tensors WNA16 to support zero-points (#14211)
|
2025-04-15 07:33:51 -06:00 |
|
|
|
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
|
d085a44082
|
Enable PTPC FP8 for CompressedTensorsW8A8Fp8MoEMethod (triton fused_moe) (#16537)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2025-04-13 14:55:18 +00:00 |
|
|
wang.yuqi
|
fbf722c6e6
|
[Frontend] support matryoshka representation / support embedding API dimensions (#16331)
|
2025-04-11 23:23:10 -07:00 |
|
|
Yong Hoon Shin
|
a3bf8d4a2b
|
[Kernel] Add tuned FusedMoE kernel config for Llama4 Scout, TP=8 on H100 (#16488)
|
2025-04-12 06:26:55 +08:00 |
|
|
Michael Goin
|
f41647ee6b
|
[Kernel] Support W8A8 channel-wise weights and per-token activations in triton fused_moe_kernel (#16366)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2025-04-11 17:54:08 +00:00 |
|
|
chaow-amd
|
9e90c9f73f
|
[Bugfix] Fix bugs of running Quark quantized models (#16236)
Signed-off-by: chaow <chaow@amd.com>
|
2025-04-11 10:18:32 -04:00 |
|
|
Chih-Chieh YangandYu Chin Fabian Lim
|
daefed052c
|
[Model] Reduce redundant computations in mamba2 blocks for Bamba-9B (#15423)
Signed-off-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com>
Co-authored-by: Yu Chin Fabian Lim <flim@sg.ibm.com>
|
2025-04-10 19:07:07 +00:00 |
|
|
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 |
|
|
yihong
|
04149cce27
|
[BugFix] fix some typos found by typos. (#16314)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
|
2025-04-09 03:43:59 -07:00 |
|
|
|
2976dc27e9
|
[Bug] [ROCm] Fix Llama 4 Enablement Bug on ROCm: V0 ROCmFlashAttentionImpl and Triton Fused MoE bugs (#16198)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
Co-authored-by: Hongxia Yang <hongxia.yang@amd.com>
Co-authored-by: kliuae <kuanfu.liu@embeddedllm.com>
|
2025-04-08 19:12:34 -07:00 |
|
|
Isotr0py
|
40b4284fe3
|
[Bugfix] Handle process_weights_after_loading for QKVCrossParallelLinear (#15328)
Signed-off-by: Isotr0py <2037008807@qq.com>
|
2025-04-08 10:02:23 -07:00 |
|
|
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 |
|
|
Michael Goin
|
21802c4b6d
|
[ROCm][Bugfix][FP8] Make fp8 quant respect fused modules mapping (#16031)
Signed-off-by: mgoin <michael@neuralmagic.com>
|
2025-04-07 21:28:14 -04:00 |
|
|
Driss Guessous
|
652907b354
|
Torchao (#14231)
Signed-off-by: drisspg <drisspguessous@gmail.com>
|
2025-04-07 19:39:28 -04:00 |
|
|
|
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 |
|
|
Jinzhen Lin
|
2fa66ef713
|
[Bugfix] fix use_atomic_add support of marlin kernel when using v1 engine (#15946)
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
|
2025-04-05 20:04:22 -07:00 |
|
|
bnellnm
|
d6fc629f4d
|
[Kernel][Minor] Re-fuse triton moe weight application (#16071)
Signed-off-by: Bill Nell <bnell@redhat.com>
|
2025-04-04 23:27:34 +00:00 |
|
|
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 |
|
|
bnellnm
|
15ba07ef25
|
[Minor] Fused experts refactor (#15914)
Signed-off-by: Bill Nell <bnell@redhat.com>
|
2025-04-03 10:19:38 -07:00 |
|
|
LukasBluebaum
|
90969fb39a
|
[Kernel] Add more dtype support for GGUF dequantization (#15879)
Signed-off-by: lukas.bluebaum <lukas.bluebaum@aleph-alpha.com>
|
2025-04-02 01:58:48 -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 |
|
|
Thien Tran
|
2039c6305b
|
[Bugfix] Fix imports for MoE on CPU (#15841)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
|
2025-04-02 03:33:55 +00:00 |
|
|
|
9ef98d527e
|
[Model][MiniMaxText01] Support MiniMaxText01 model inference (#13454)
Signed-off-by: qscqesze <475517977@qq.com>
Co-authored-by: qingjun <qingjun@minimaxi.com>
Co-authored-by: qscqesze <475517977@qq.com>
|
2025-04-01 16:23:55 -04:00 |
|
|
bnellnm
|
e59ca942f5
|
Add option to use DeepGemm contiguous grouped gemm kernel for fused MoE operations. (#13932)
Signed-off-by: Bill Nell <bnell@redhat.com>
|
2025-04-01 12:07:43 -04:00 |
|
|
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 |
|
|
Alexey Kiryushin
|
63d8eabed0
|
[Bugfix]: Fix is_embedding_layer condition in VocabParallelEmbedding (#15824)
Signed-off-by: alexwl <alexey.a.kiryushin@gmail.com>
|
2025-03-31 22:57:59 -07:00 |
|
|
TJian
|
4965ec42d2
|
[FEAT] [ROCm] Add AITER int8 scaled gemm kernel (#15433)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2025-03-29 03:33:56 -07:00 |
|
|
Nicolò Lucchesi
|
da461f3cbf
|
[TPU][V1][Bugfix] Fix w8a8 recompiilation with GSM8K (#15714)
Signed-off-by: NickLucche <nlucches@redhat.com>
|
2025-03-28 21:13:06 -07:00 |
|
|
Gregory ShtrasbergandLuka Govedič
|
4d0ec37267
|
[Quantization][FP8] Adding support for fp8 gemm layer input in fp8 (#14578)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
|
2025-03-28 02:58:16 +00:00 |
|
|
Wes
|
4ae17bf1e2
|
Revert "Use Cache Hinting for fused_moe kernel (#15511)" (#15645)
Signed-off-by: Wes Medford <wryanmedford@gmail.com>
|
2025-03-27 19:45:55 -07:00 |
|
|
Jee Jee Li
|
726efc6a32
|
[Quantization][V1] BitsAndBytes support V1 (#15611)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-03-28 10:12:47 +08:00 |
|
|
|
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 |
|
|
ElizaWszolaandLucas Wilkinson
|
9239bf718e
|
[Kernel] CUTLASS grouped gemm fp8 MoE kernel (#13972)
Signed-off-by: ElizaWszola <eliza@neuralmagic.com>
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Co-authored-by: Lucas Wilkinson <wilkinson.lucas@gmail.com>
|
2025-03-27 00:54:44 +00:00 |
|
|
Wes
|
7a888271f5
|
Use Cache Hinting for fused_moe kernel (#15511)
|
2025-03-26 23:21:34 +00:00 |
|
|
vllmellmandtjtanaa
|
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 |
|
|
Tyler Michael Smith
|
b5269db959
|
Revert "Fix non-contiguous input passed to Marlin kernel (#15319)" (#15398)
|
2025-03-24 20:43:51 -07:00 |
|