 Wei ZhaoandGitHub
|
986edc858a
|
[Bugfix] Fix DeepSeek v4 topk numerical issue for unaligned max-model-len (#42169)
|
2026-05-09 20:30:08 -07:00 |
|
|
|
00b0618a03
|
Use CU_MEMCPY_SRC_ACCESS_ORDER_ANY for batch KV cache swaps (#39306)
Signed-off-by: Itay Etelis <itay.etelis@ibm.com>
Signed-off-by: Itay Etelis <etelis2019@gmail.com>
Signed-off-by: Itay Etelis <92247226+Etelis@users.noreply.github.com>
Co-authored-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
Co-authored-by: Itay Etelis <etelis2019@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-05-10 05:57:09 +03:00 |
|
|
|
6881c754e1
|
use HIP_VERSION variables to guard against duplicate atomicAdd definitions (#41802)
Signed-off-by: Philip Maybank <pmaybank@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-05-08 18:44:37 -04:00 |
|
|
Li, JiangandGitHub
|
b3945cc316
|
[CPU] Bump up to the latest CPU kernels (#41924)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-05-07 05:45:59 -07:00 |
|
|
|
20cac26b19
|
[ROCm] Enable SimpleCPUOffloadConnector on ROCm (#40549)
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-05-06 20:52:02 -07:00 |
|
|
Yongye ZhuandGitHub
|
80d5e7d103
|
[Bugfix] Fix condition to clear persistent topk so that it can be captured regardless (#41665)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-05-06 16:17:48 -07:00 |
|
|
|
66d1cc0c77
|
fix(rocm): remove workaround causing invalid argument on Qwen3.5 with TP=2 (#40686)
Co-authored-by: Test User <test@example.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-05-06 01:38:32 -07:00 |
|
|
|
e87e09a50a
|
[Feat] dnnl build for AVX2 W8A8 Int8 (#41318)
Signed-off-by: Li, Tianmu <tianmu.li@intel.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
|
2026-05-06 15:28:02 +08:00 |
|
|
Yuwen ZhouandGitHub
|
809b98e5b7
|
[CPU] Add FP8 W8A16 linear support (#41186)
Signed-off-by: yuwenzho <yuwen.zhou@intel.com>
|
2026-05-06 07:05:27 +00:00 |
|
|
|
e47c98ef7a
|
[Fix] Add missing stubs from cpu fp8 attention changes (#41387)
Signed-off-by: Li, Tianmu <tianmu.li@intel.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
|
2026-05-06 12:16:27 +08:00 |
|
|
|
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 |
|
|
|
420b0a5c95
|
[Hardware][Power]Add Power VSX Attention Backend and fix l2 Cache Crash (#40451)
Signed-off-by: Akash Kaothalkar <akashkaothalkar@akashs-mbp.bl1-in.ibm.com>
Signed-off-by: Akash Kaothalkar <akash.kaothalkar@ibm.com>
Signed-off-by: Akash kaothalkar <akash.kaothalkar@ibm.com>
Co-authored-by: Akash Kaothalkar <akashkaothalkar@akashs-mbp.bl1-in.ibm.com>
Co-authored-by: Akash Kaothalkar <akash.kaothalkar@ibm.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
|
2026-05-04 20:51:09 -07:00 |
|
|
Yongye ZhuandGitHub
|
edd60ac93a
|
[Bugfix] Fix persistent_topk inter-CTA init race on RadixRowState (#41444)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-05-01 14:42:52 -07:00 |
|
|
|
a3c83ff2fd
|
Faster per-token fp8 group quant packed kernel for blackwell (#41326)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2026-04-30 18:09:55 -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 |
|
|
|
a749a33d8d
|
[Bugfix] Fix persistent_topk cooperative deadlock at TopK=1024 (#41189)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-04-29 21:03:45 -07:00 |
|
|
Cyrus LeungandGitHub
|
4a42aba380
|
[CI/Build] Enable FP8 on NVIDIA Thor (#39712)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2026-04-29 09:48:52 -07:00 |
|
|
|
22524f7a92
|
[Feat] CPU fp8 attn for AMX/AVX-512 (#39445)
Signed-off-by: Li, Tianmu <tianmu.li@intel.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
|
2026-04-29 20:43:21 +08:00 |
|
|
Jee Jee LiandGitHub
|
a269744e9f
|
[Bugfix] Fix rope (#41113)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-04-28 22:42:35 -07:00 |
|
|
Yongye ZhuandGitHub
|
706a04d34b
|
[DSV4] Add silu clamp limit to shared expert (#40950)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-04-27 00:37:43 -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 |
|
|
Woosuk KwonandGitHub
|
7d3195ea9f
|
[Bugfix] Fix IMA in DSA + MTP (#40772)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-04-24 01:40:20 -07:00 |
|
|
Xin YangandGitHub
|
cf8a613a87
|
Support only half types for concat_mla_q kernel (#37892)
Signed-off-by: Xin Yang <xyangx@amazon.com>
|
2026-04-23 23:51:05 -07:00 |
|
|
|
2f314bc5e6
|
[CPU] Added faster exp routine for lower precision data types. (#38112)
Signed-off-by: Anna Mayne <anna.mayne@arm.com>
Co-authored-by: Fadi Arafeh <fadi.arafeh@arm.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
|
2026-04-23 13:14:44 +00:00 |
|
|
Matthias GehreandGitHub
|
4b7869d6bc
|
[ROCm] Add gfx1102/gfx1103 support (#40037)
Signed-off-by: Matthias Gehre <matthias.gehre@amd.com>
|
2026-04-23 01:32:04 -07:00 |
|
|
lyd1992andGitHub
|
04eac6ba24
|
[Bugfix][CPU][RISC-V] Clamp exp() input to prevent NaN (#40428)
Signed-off-by: liuyudong <liuyudong@iscas.ac.cn>
|
2026-04-22 09:38:18 +00:00 |
|
|
Jakub ZakrzewskiandGitHub
|
6fbec8ed47
|
[Bugfix][Kernel] nvfp4 cutlass MoE: fix nvfp4 experts quant out-of-bounds read for expert counts not divisible by 4 or 16 (#40351)
Signed-off-by: Jakub Zakrzewski <jzakrzewski@nvidia.com>
|
2026-04-21 19:06:09 +00:00 |
|
|
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 |
|
|
velonica0andGitHub
|
ec7aafc02a
|
[CPU][RISC-V] Support multiple RVV VLEN targets via compile-time dispatch (#39478)
Signed-off-by: velonica0 <like@mail.nankai.edu.cn>
|
2026-04-20 14:36:59 +08:00 |
|
|
|
d0359f3e04
|
[Bugfix] Guard mxfp4_experts_quant bindings on ENABLE_NVFP4_SM100 (#40191)
Signed-off-by: ultranationalism <www913363043@gmail.com>
Signed-off-by: mgoin <mike.goin12@gmail.com>
Co-authored-by: mgoin <mike.goin12@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-04-18 13:58:46 -07:00 |
|
|
Michael GoinandGitHub
|
a8bffaa133
|
[Kernel] Add MXFP4 W4A4 CUTLASS MoE kernel for SM100 (#37463)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-04-17 16:42:32 -07:00 |
|
|
sychen52andGitHub
|
6b2b7bd0eb
|
Add nvfp4 support to reshape_and_cache_flash (#37332)
Signed-off-by: Shiyang Chen <shiychen@nvidia.com>
|
2026-04-17 07:28:00 -07:00 |
|
|
Li, JiangandGitHub
|
d02421a7db
|
[CPU] Refactor CPU affinity and memory management (#39781)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-04-17 21:01:08 +08:00 |
|
|
R3hankhanandGitHub
|
4b7ca37bd4
|
[CPU][IBM Z][Dockefile][Docs] Fix s390x builds for torch 2.11 and update docs for s390x (#39910)
Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com>
|
2026-04-15 22:26:21 -07:00 |
|
|
|
445b7093fd
|
[perf][cpu] Accelerate BF16 GELU with LUT impl on Arm CPUs (#37469)
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-04-15 22:26:17 -07:00 |
|
|
|
4beeb0689c
|
fused qknorm+rope kernel optimization for SM9.0 (#37376)
Signed-off-by: EricccYang <yangyang4991@gmail.com>
Signed-off-by: Kaicheng Yang <53411596+EricccYang@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
|
2026-04-12 19:58:37 -07:00 |
|
|
|
bd8bd52308
|
[Bugfix] Runtime driver check for cuMemcpyBatchAsync in swap_blocks_batch (#38919)
Signed-off-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-04-11 11:02:34 -06:00 |
|
|
Wei ZhaoandGitHub
|
59b2f7b640
|
[Perf] Fuse Zero Initializer for FP8 DeepGemm Block Quant Kernel (#39547)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-04-11 07:16:51 -07:00 |
|
|
Jee Jee LiandGitHub
|
ecd1ea1363
|
[Kernel] Porting the TRTLLM minimax_allreduce_rms kernels (#37045)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-04-11 00:20:20 +08:00 |
|
|
Isotr0pyandGitHub
|
58c0a928c9
|
[Bugfix] Fix broken explicit unquantized kv cache dtype support (#38922)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-04-09 22:27:53 -07:00 |
|
|
|
f83de7196f
|
[BugFix] Fix OOB read in CUTLASS grouped GEMM with epilogue (#38571)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-04-09 23:52:52 -04:00 |
|
|
Ganesh RandGitHub
|
445a2a4d1a
|
feat(cpu): add CPU support for draft model speculative decoding (#32662)
Signed-off-by: R <Ganesh.R@amd.com>
|
2026-04-10 11:49:52 +08:00 |
|
|
Yongye ZhuandGitHub
|
2e98406048
|
[Refactor] Improve indexer decode path metadata preparation (#38865)
|
2026-04-08 20:49:15 -07:00 |
|
|
|
b55d830ec7
|
[Perf][Kernel] Persistent TopK scheduler: unified CUDAGraph-safe kernel with dynamic per-row dispatch - DeepSeek-V3.2 DSA decode (#37421)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
|
2026-04-08 13:35:57 -04:00 |
|
|
Gregory ShtrasbergandGitHub
|
56c976c1b5
|
[ROCm] Enable fused_silu_mul_block_quant on ROCm (#38817)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
|
2026-04-08 11:23:32 -05:00 |
|
|
Andrey TalmanandGitHub
|
2111997f96
|
[release 2.11] Update to torch 2.11 (#34644)
|
2026-04-07 18:55:48 -07:00 |
|
|
Kyle MylonakisandGitHub
|
7b9de7c892
|
[Bugfix] Correct mistake in chained comparison in static assert logic (#38699)
Signed-off-by: Kyle Mylonakis <kyle@protopia.ai>
|
2026-04-07 18:24:39 +08:00 |
|
|
Wentao YeandGitHub
|
062f1a2d70
|
[Bug] Fix compile error for swap_blocks_batch in CUDA 13 (#38915)
|
2026-04-03 16:56:38 -07:00 |
|
|
NecofishandGitHub
|
580090db6b
|
[Kernel] Add swapAB support for SM120 CUTLASS blockwise FP8 GEMM (#38325)
|
2026-04-03 15:49:59 +02:00 |
|
|
Anton IvanovandGitHub
|
abebd9323d
|
[CPU] Replace OMP initialization (#36487)
Signed-off-by: Anton Ivanov <anton.ivanov@cambridgegreys.com>
|
2026-04-03 18:42:43 +08:00 |
|