|
89e99202f2
|
[CPU][Perf]Added tanh AOR for faster gelu activations. (#44639)
Signed-off-by: Anna Mayne <anna.mayne@arm.com>
Signed-off-by: almayne <anna.mayne@arm.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
|
2026-06-30 23:24:40 -07:00 |
|
|
Woosuk KwonandGitHub
|
f098ee70c7
|
[GLM5] Support FlashMLA FP8 KV cache (Hopper & Blackwell) (#47090)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-06-30 18:13:21 -07:00 |
|
|
|
aab7af0bcb
|
[Bugfix][ROCm][MLA] Pass q/kv dtypes to get_mla_metadata_v1 in FP8 decode (#46997)
Signed-off-by: pei.zhang <pei.zhang@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-06-30 05:31:16 -07:00 |
|
|
|
8e9d70fdd5
|
[Kernel][XPU] Adjust kernel unit tests for XPU (#45140)
Signed-off-by: Dobrzyniewicz, Agata <agata.dobrzyniewicz@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-06-30 09:57:27 +00:00 |
|
|
Kunshang JiandGitHub
|
fb42e5219e
|
[Platform] Replace torch.cuda.mem_get_info with torch.accelerator.get_memory_info (#44825)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
|
2026-06-30 14:39:52 +08:00 |
|
|
zhrrrandGitHub
|
61ab70ec3b
|
[Model Runner V2] support mamba hybrid models align prefix cache (#42406)
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
|
2026-06-29 14:09:16 -07:00 |
|
|
Xiaohong (Sean) ChenandGitHub
|
49e28e8e91
|
[Kernel][Helion][1/N] Add Helion kernel for fused_qk_norm_rope (#44010)
Signed-off-by: Sean Chen <seachen@redhat.com>
|
2026-06-29 22:54:15 +08:00 |
|
|
Yuwen ZhouandGitHub
|
58d6a6e60a
|
[CPU] Support cpu compressed-tensor w8a8 int8 moe (#42920)
Signed-off-by: yuwenzho <yuwen.zhou@intel.com>
Signed-off-by: Yuwen Zhou <yuwen.zhou@intel.com>
|
2026-06-29 03:04:05 +00:00 |
|
|
|
a2abce646f
|
[EPLB] Mask padding in EPLB load recording (#38128)
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Signed-off-by: Markov Ilya <markovilya19@gmail.com>
Co-authored-by: Markov Ilya <markovilya19@gmail.com>
|
2026-06-28 19:43:58 -07:00 |
|
|
Woosuk KwonandGitHub
|
89876b0c54
|
[GLM5] Implement op fusion for GLM5/DSV3.2 (#46876)
|
2026-06-28 08:17:39 -07:00 |
|
|
xiaolinchenandGitHub
|
35e3850fa9
|
[Bugfix][Test] Fix test_flashinfer_cutlass_mxfp4_fused_moe on sm90 (stale weight/scale interleave) (#46915)
Signed-off-by: wentian-byte <2990624738@qq.com>
|
2026-06-27 14:30:10 -04:00 |
|
|
|
867fd5e8ed
|
[ROCm][Perf] Use flydsl moe with Minimax-M3 mxfp8 weights on gfx950 and implemented moe-backend selection (#46184)
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Tan Pin Siang <tanpinsiang@gmail.com>
|
2026-06-27 10:22:57 +00:00 |
|
|
Divakar VermaandGitHub
|
68ee8300a0
|
[ROCm][CI]Fix test_concat_and_cache_mla_rope_fused on ROCm (#46409)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-06-27 12:38:13 +08:00 |
|
|
Divakar VermaandGitHub
|
00e045b7c7
|
[ROCm][CI TG] refactor and fix deepep_moe test group (#46758)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-06-27 10:45:23 +08:00 |
|
|
Divakar VermaandGitHub
|
17a71d8702
|
[ROCm][CI] Relax fused layernorm quant test tolerances for one-ULP outliers (#46658)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-06-27 10:44:29 +08:00 |
|
|
MattandGitHub
|
95e6442a6b
|
[Hardware][AMD][CI] Fix Kernels Quantization test timeout (#46859)
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
|
2026-06-26 15:19:16 -05:00 |
|
|
|
d980a3cc6e
|
[ROCm] Fix AITER_UNIFIED_ATTN Dispatching After AITER Bump (#46780)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Co-authored-by: Rohan138 <rohanpotdar138@gmail.com>
|
2026-06-26 02:09:56 -07:00 |
|
|
fxmarty-amdandGitHub
|
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 |
|
|
|
02a1f23711
|
[DFlash] Fuse precompute kv per-layer rmsnorms (#46761)
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-25 19:32:07 -07:00 |
|
|
|
e8c24a7695
|
[Kernel] Vectorized fp32 moe_sum reduction and support any topk (#46643)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-06-25 14:02:28 -07:00 |
|
|
|
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 |
|
|
|
1aad125815
|
[CPU] Enable chunked prefill and prefix caching for qwen3.5 (#46202)
Signed-off-by: Li, Tianmu <tianmu.li@intel.com>
Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
|
2026-06-25 03:49:21 +00:00 |
|
|
Kaihang JiangandGitHub
|
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 |
|
|
cyqandGitHub
|
e06a83445c
|
[Bugfix] Normalize slashes in Helion GPU names (#46101)
Signed-off-by: cyq <15000851237@163.com>
|
2026-06-24 18:22:49 -05:00 |
|
|
|
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 |
|
|
|
b3a688cb9e
|
[ROCm] Fix OOB During Model Warmup With ROCM_ATTN and MRV2 (#46548)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: Matthew Wong <Matthew.Wong2@amd.com>
|
2026-06-24 10:53:21 -05:00 |
|
|
Fadi ArafehandGitHub
|
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 |
|
|
Andreas KaratzasandGitHub
|
549c7074cd
|
[ROCm][CI] Skip the MoE Marlin tile-padding helper assertion (#46580)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-06-24 07:31:33 +00:00 |
|
|
Roberto L. CastroandGitHub
|
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 |
|
|
|
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 |
|
|
|
6691f087a6
|
[Minimax-M3] BF16/FP8 Indexer using MSA (#45892)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
|
2026-06-23 10:28:49 -07:00 |
|
|
|
84586c9acc
|
[ROCm][CI] fix fp8 range in vit_fp8_quant (#46410)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Signed-off-by: Divakar Verma <137818590+divakar-amd@users.noreply.github.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-06-23 11:34:21 -05:00 |
|
|
Micah WilliamsonandGitHub
|
156b12667c
|
[ROCm][CI] Skip Quark mxfp4 tests unless Quark version is compatible with Torch version (#46431)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
|
2026-06-23 22:26:39 +08:00 |
|
|
|
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 |
|
|
Mohammad Miadh AngkadandGitHub
|
d1a38c2762
|
[Kernel][Performance] Add FlashInfer cutedsl NVFP4 GEMM backend (#42235)
Signed-off-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
|
2026-06-22 16:17:18 -04:00 |
|
|
Yifan QiaoandGitHub
|
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 SarviandGitHub
|
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 |
|
|
|
db32b53e30
|
[SpecDecode] Support DFlash with FlashInfer (#43081)
Signed-off-by: gss <2783977641@qq.com>
Co-authored-by: gss <2783977641@qq.com>
|
2026-06-22 04:55:30 +00:00 |
|
|
MattandGitHub
|
4f0d0049a0
|
[Hardware][AMD][CI] Fix Kernels Attention test groups (#46080)
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
|
2026-06-21 17:10:51 -05:00 |
|
|
MattandGitHub
|
50241602fd
|
[Hardware][AMD][CI] Fix gfx942 Kernels MoE test group (#46298)
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
|
2026-06-21 16:45:37 -05:00 |
|
|
Jee Jee LiandGitHub
|
745bba5ea8
|
[Model]Fix MiniMaxM2ForCausalLM perf regression (#45935)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-06-22 00:28:52 +08:00 |
|
|
JasonLi314andGitHub
|
93bad11912
|
[Bugfix] Fix gridDim.y overflow for large row counts (#45255)
Signed-off-by: Jason Li <li.jason.cs@gmail.com>
|
2026-06-19 23:27:45 -04:00 |
|
|
Micah WilliamsonandGitHub
|
4a083cc858
|
[ROCm][CI] Pin test_rocm_compressed_tensors_w8a8 to TRITON_ATTN (#46180)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
|
2026-06-19 15:20:06 -05:00 |
|
|
HumphreyandGitHub
|
4583630b56
|
[Bugfix][Kernel] Check output alignment in vectorize_with_alignment (fixes misaligned-address crash for non-multiple-of-8 head sizes) (#45466)
Signed-off-by: HumphreySun98 <humphreysun98@gmail.com>
|
2026-06-18 16:58:22 +00:00 |
|
|
|
afdcbd5d39
|
[ROCm][DSv4] Functional fixes for DeepSeek V4 on MI300X/MI325X (#45681)
Signed-off-by: ganyi <ygan@amd.com>
Signed-off-by: Markus Hartikainen <markus.hartikainen@amd.com>
Signed-off-by: Tuukka Sarvi <tuukka.sarvi@amd.com>
Co-authored-by: ganyi <ygan@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Markus Hartikainen <markus.hartikainen@amd.com>
Co-authored-by: Jin Tao <jintao12@amd.com>
|
2026-06-18 12:21:14 +00:00 |
|
|
|
b4c80ec0fd
|
[Refactor] Remove dead cutlass mxfp8 code (#44681)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
|
2026-06-17 21:18:25 -07:00 |
|
|
Wentao YeandGitHub
|
2659f60a1a
|
[Refactor] Remove dead quantization code and tests (#45454)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-06-17 16:12:01 -04:00 |
|
|
Wentao YeandGitHub
|
9c7c74bf10
|
[Log] Update deepgemm log (#45857)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-06-17 15:34:22 +00:00 |
|
|
|
46f74e144b
|
[Kernel][Helion][1/N] Add Helion kernel for rms_norm_dynamic_per_token_quant (#34432)
Signed-off-by: Sean Chen <seachen@redhat.com>
Co-authored-by: Yanan Cao <gmagogsfm@gmail.com>
|
2026-06-17 23:03:54 +08:00 |
|
|
Wentao YeandGitHub
|
0a7bacdcac
|
[DSv4 Perf] DSv4 flashinfer sparse index cache for metadata, 2%~4% TTFT improvement (#45863)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-06-17 10:55:48 -04:00 |
|