 Fadi ArafehandGitHub
|
f1073c050c
|
[CPU][BugFix] Multiple fixes to w4a8_int8 CPU MoE path (#46739)
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
|
2026-07-06 05:39:20 +00:00 |
|
|
|
6e64c1bab1
|
[10c/n] Migrate MoE kernels to torch stable ABI (#44565)
Signed-off-by: Chris Leonard <chleonar@redhat.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
|
2026-06-10 23:02:26 -07:00 |
|
|
|
59d0236193
|
[10b/n] Migrate custom all-reduce, DeepSeek V4 fused MLA, MiniMax reduce-RMS, and MXFP8 MoE to libtorch stable ABI (#44365)
Signed-off-by: Chris Leonard <chleonar@redhat.com>
Signed-off-by: Shengqi Chen <harry-chen@outlook.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
|
2026-06-04 00:29:46 +08:00 |
|
|
Wentao YeandGitHub
|
64e1218673
|
[Perf] Optimize moe permute by pre-allocate buffer, 9~14% kernel performance improvement (#43014)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-05-28 06:18:26 -07:00 |
|
|
Jee Jee LiandGitHub
|
d4004455d2
|
[Kernel] Remove NormGateLinear (#43554)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-05-25 09:49:19 +00:00 |
|
|
Wentao YeandGitHub
|
00e20e76f7
|
[Refactor] Remove dead cuda kernels (#42767)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-05-18 11:14:21 -07:00 |
|
|
|
e3aeee5ff8
|
[Bugfix] moe lora align kernel grid (#40131)
Signed-off-by: TheDuyIT <nduy250299@gmail.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Signed-off-by: dtnguyen <dtnguyen@nvidia.com>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-05-18 00:17:53 -07:00 |
|
|
|
06d020bb6e
|
[Bugfix] Fix SM121 (DGX Spark) exclusion from Marlin/CUTLASS FP8 paths (#35568)
Signed-off-by: Blake Ledden <blake@secondnaturecomputing.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Pavani Majety <pmajety@nvidia.com>
|
2026-05-15 10:59:00 -07:00 |
|
|
Wentao YeandGitHub
|
6548560496
|
[Compile] Fix compile warning with topk softplus sqrt (#41261)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-05-14 05:12:50 -07:00 |
|
|
|
0a65d46628
|
[DSV4] Fuse norm and router for low latency scenario (#41263)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: jeejeelee <jeejeelee@verda-b300-05.datacrunch.io>
Co-authored-by: jeejeelee <jeejeelee@verda-b300-05.datacrunch.io>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-05-14 05:11:02 -07:00 |
|
|
|
628c436301
|
[New Model][ROCm] Add AMD support for DeepSeek V4 (#40871)
Signed-off-by: ganyi <ygan@amd.com>
Signed-off-by: whx-sjtu <xiaowang990929@gmail.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Signed-off-by: tjtanaavllm <tunjian.tan@amd.com>
Co-authored-by: ganyi <ygan@amd.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaavllm <tunjian.tan@amd.com>
|
2026-05-05 08:55:37 -07:00 |
|
|
Woosuk KwonandGitHub
|
9c61864bf8
|
[DeepSeek] Use torch.mm for bf16xbf16->fp32 gemm (#41300)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-04-30 16:28:57 -07:00 |
|
|
+8
|
4d51588e23
|
[Feat] DeepSeek V4 Rebased (#40860)
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Signed-off-by: qizixi <zixi@inferact.ai>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Yongye Zhu <yongye@inferact.ai>
Co-authored-by: Simon Mo <simon@inferact.ai>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Giancarlo Delfin <gdelfin@inferact.ai>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roy Wang <yasong.wang@inferact.ai>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Zhewen Li <jerven.vllm@gmail.com>
Co-authored-by: Zijing Liu <liuzijing2014@gmail.com>
Co-authored-by: khluu <khluu000@gmail.com>
Co-authored-by: qizixi <zixi@inferact.ai>
Co-authored-by: Zhewen Li <zhewenli@inferact.ai>
|
2026-04-26 18:31:08 -07:00 |
|
|
Jhao-Ting ChenandGitHub
|
28c222157b
|
fix: clamp NaN/Inf in topk_softmax to prevent duplicate expert IDs (#39391)
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
|
2026-04-21 15:04:41 +04:00 |
|
|
Xin YangandGitHub
|
9bd7231106
|
Revert "[Kernel] Add gpt-oss Router GEMM kernel (#37205)" (#38778)
Signed-off-by: Xin Yang <xyangx@amazon.com>
|
2026-04-01 22:02:32 -07:00 |
|
|
Michael GoinandGitHub
|
db5d0719e1
|
[Kernel] Add MXFP8 to Marlin GEMM/MoE and refactor Mxfp8LinearOp (#34664)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-04-01 09:41:42 -07:00 |
|
|
IriKaandGitHub
|
148a5c1226
|
[Bugfix]fix output Nan/Inf in marlin if dtype=float16 (#33972)
Signed-off-by: IriKa Qiu <qiujie.jq@gmail.com>
|
2026-03-27 16:36:08 -07:00 |
|
|
Xin YangandGitHub
|
b1169d7be8
|
[Kernel] Add gpt-oss Router GEMM kernel (#37205)
Signed-off-by: Xin Yang <xyangx@amazon.com>
|
2026-03-18 08:15:56 -07:00 |
|
|
Wentao YeandGitHub
|
e855d380fa
|
[Compile] Fix compile warning in moe_permute (#36529)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-03-16 10:16:14 -04:00 |
|
|
|
6a895197fa
|
[Bugfix][CI] fix typos (#34934)
Signed-off-by: 1195343015 <1195343015@qq.com>
Signed-off-by: Jiayi Yan <66017932+1195343015@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-03-05 17:05:46 +00:00 |
|
|
|
cb21972a97
|
[Kernel] Integrate SM100 MXFP8 blockscaled grouped MM and quant kernels (#34448)
Signed-off-by: EdalatiAli <aliedalati@cohere.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-03-01 23:31:19 -08:00 |
|
|
roikoren755andGitHub
|
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 |
|
|
Xin YangandGitHub
|
3bbb2046ff
|
[Bugfix] Fix expert_ids padding values in moe_align_block_size kernel (#35161)
Signed-off-by: Xin Yang <xyangx@amazon.com>
|
2026-02-24 17:14:24 -08:00 |
|
|
Michael GoinandGitHub
|
3ef9fd0f98
|
[Bugfix] Fix DSV3 kernels breaking _C and _moe_C on unsupported arches (#35123)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-02-23 17:11:27 -08:00 |
|
|
|
8435b2e049
|
[ModelBash][DSV3] Add TRTLLM DSV3 Router GEMM kernel (6% B1 Speedup) (#34302)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
|
2026-02-23 14:02:26 +00:00 |
|
|
Xin YangandGitHub
|
b1c4f0b265
|
[Kernel] Optimize grouped topk kernel (#34206)
Signed-off-by: Xin Yang <xyangx@amazon.com>
|
2026-02-20 01:34:45 -08:00 |
|
|
Wentao YeandGitHub
|
77c09e1130
|
[Refactor] Remove align block size logic in moe_permute (#33449)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-02-06 10:57:06 -08:00 |
|
|
|
fedf64332e
|
[Bugfix]: Fix display errors in TORCH_CHECK messages (#32942)
Signed-off-by: linhaifeng <1371675203@qq.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-01-31 09:48:48 -08:00 |
|
|
Wentao YeandGitHub
|
c4e744dbd4
|
[Perf] Optimize moe_permute for CUTLASS FP8 (#32892)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-01-28 10:15:24 -08:00 |
|
|
Michael GoinandGitHub
|
4561f13985
|
[Refactor] Rename gptq_marlin to marlin to match MoE (#32952)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-01-23 16:48:12 -05:00 |
|
|
Xin YangandGitHub
|
63227accf5
|
[Kernel] Add topk_sigmoid kernel (#31246)
Signed-off-by: Xin Yang <xyangx@amazon.com>
|
2026-01-21 22:49:51 +00:00 |
|
|
Wentao YeandGitHub
|
6c97b9b9b6
|
[Perf] Only clone when needed for moe_permute (#32273)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-01-20 11:34:39 -05:00 |
|
|
Michael GoinandGitHub
|
83239ff19a
|
Add thread_n=64 support to Marlin MoE (#32360)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-01-15 16:45:44 -08:00 |
|
|
Wentao YeandGitHub
|
f28125d87b
|
[Perf] Optimize grouped topk kernel, 1.2%~2% E2E Throughput improvement (#32058)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-01-13 10:58:18 -08:00 |
|
|
|
0ada960a20
|
[Kernel] Support bias type in grouped_topk kernel (#31781)
Signed-off-by: Xin Yang <xyangx@amazon.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-01-07 12:16:32 -08:00 |
|
|
|
2f4bdee61e
|
[Quantization][MoE] remove unused ep logic from moe marlin (#31571)
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-01-06 09:07:19 -08:00 |
|
|
|
ce96857fdd
|
[Kernel][Quantization][MoE] add marlin kernel support for turing (sm75) (#29901)
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2025-12-16 14:35:28 -08:00 |
|
|
|
f21f5ea38c
|
[Refactor] Small refactor for group topk (#30562)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2025-12-16 14:50:59 -05:00 |
|
|
Bhanu Prakash VoutharojaandGitHub
|
6a6fc41c79
|
gptq marlin quantization support for fused moe with lora (#30254)
Signed-off-by: Bhanu068 <voutharoja.bhanu06@gmail.com>
|
2025-12-12 02:27:22 +00:00 |
|
|
Wentao YeandGitHub
|
61249b177d
|
[Refactor] Remove useless syncwarp (#30510)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-12-11 17:43:41 -05:00 |
|
|
gnovackandGitHub
|
ea657f2078
|
Lora MoE Align Improvements (#29257)
Signed-off-by: gnovack <gnovack@amazon.com>
|
2025-12-09 10:35:16 +08:00 |
|
|
Wentao YeandGitHub
|
0ee6416f67
|
[Perf] Optimize group_topk kernel, 1.9% Throughput improvement, 2.1% TPOT improvemnt (#30159)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-12-08 19:44:01 -05:00 |
|
|
|
879ddb09c3
|
[Kernel][MoE] optimize moe_align_block_size (#29642)
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-12-07 01:58:47 -08:00 |
|
|
Zhang XiangzeandGitHub
|
13ea39bc09
|
[CPU]Parallelize over tokens in int4 moe (#29600)
Signed-off-by: Zhang Xiangze <Xiangze.Zhang@arm.com>
|
2025-12-02 06:21:39 +00:00 |
|
|
|
1656ad3704
|
[Kernel][Quantization] add w4a8 support for marlin kernel (#24722)
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin@redhat.com>
|
2025-11-29 07:19:33 -08:00 |
|
|
|
a67dec7cba
|
[Bugfix] fix IMA issue in certain cases of the moe marlin kernel (#28619)
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2025-11-26 19:02:21 -08:00 |
|
|
|
0852527647
|
[Perf][DeepSeek] Add sigmoid+bias fusion to fused_grouped_topk from TRTLLM (#28124)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2025-11-07 18:20:55 -08:00 |
|
|
xiangze-armandGitHub
|
f32cbc9a0c
|
[CPU]Improve dynamic 4bit moe performance (#27240)
Signed-off-by: Zhang Xiangze <Xiangze.Zhang@arm.com>
|
2025-11-04 06:33:23 +00:00 |
|
|
|
294c805f1d
|
Early exit for MoE LoRA kernels (#27131)
Signed-off-by: gnovack <gnovack@amazon.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-11-03 20:22:17 +08:00 |
|
|
|
8e4ca4d14e
|
Bugfix - pass 'max_num_tokens_padded' into 'moe_lora_align_block_size' (#27311)
Signed-off-by: gnovack <gnovack@amazon.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-10-22 12:23:57 +00:00 |
|