 eeechoandBaizhou Zhang
|
19c30dff56
|
[SM120] DeepSeek-V4: DeepGEMM paged-MQA indexer +FP4 MoE+ page-split (#29927)
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
|
2026-09-02 15:49:59 -07:00 |
|
|
YAMY
|
982aa8acfc
|
[Bugfix] Load Qwen3.5 MTP embedding under PP (#37471)
|
2026-09-02 15:19:40 -07:00 |
|
|
YAMY
|
3c9cea8f10
|
[EAGLE] Prune draft-extend logits to selected rows (#35546)
|
2026-09-02 15:10:08 -07:00 |
|
|
YAMY
|
fe45af1e6f
|
perf(gdn): select ReplaySSM verify loop unrolling by shape (#36970)
|
2026-09-02 15:07:49 -07:00 |
|
|
cctry
|
3a855b050a
|
fix(disagg): poll receivers during decode preallocation (#37483)
|
2026-09-02 14:26:40 -07:00 |
|
|
cctry
|
ad6e830858
|
[Bugfix] Key CUDA graph dedup signatures on kernel function identity (#37657)
|
2026-09-02 14:24:31 -07:00 |
|
|
Liangsheng Yin
|
19c7679e9e
|
[mem_cache] Make free_swa sync-free on page_size == 1 (#36723)
|
2026-09-02 14:18:22 -07:00 |
|
|
JoeandBBuf
|
acea43079f
|
Fix native MoE handling of noncontiguous top-k IDs (#36407)
Co-authored-by: BBuf <1182563586@qq.com>
|
2026-09-02 14:16:19 -07:00 |
|
|
|
f8cbf000f4
|
[AMD] Enable FP4 indexer for Deepseek V4 (#37353)
Co-authored-by: 1am9trash <1am9trash@gmail.com>
Co-authored-by: AMD-yanfeiwang <256076023+AMD-yanfeiwang@users.noreply.github.com>
Co-authored-by: Thomas Wang <thomawan@amd.com>
|
2026-09-02 09:45:08 -07:00 |
|
|
Mick
|
f6aed6ec53
|
[diffusion] doc: rewrite stale diffusion compatibility matrix (#36987)
|
2026-09-02 23:42:54 +08:00 |
|
|
Kevin MiandClaude Fable 5
|
f586654518
|
[diffusion] feat: support FastH3 (4-step VSA-distilled MiniMax-H3) with a VSA-H3 attention backend (#37480)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-09-02 21:39:54 +08:00 |
|
|
Liangsheng Yin
|
862a909a08
|
[Fix] Lock PP dynamic-chunk profiling requests before releasing through the tree cache (#37509)
|
2026-09-02 02:09:01 -07:00 |
|
|
Liangsheng Yin
|
ebfd8c60e5
|
[CI] Install sgl-eval from PyPI through the test extra (#37504)
|
2026-09-02 01:45:25 -07:00 |
|
|
Shuwen WangandClaude Opus 5
|
fe3d4b9bbb
|
fix: restore missing get_component_forced_attn_backend import in minimax_h3 (#37566)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-02 15:58:31 +08:00 |
|
|
|
4b329482e8
|
[diffusion] feat: support cube sparse attention for minimax h3 (#34893)
Co-authored-by: zhenaozhenfu <zhenaozhenfu@minimaxi.com>
Co-authored-by: Reynor <reynor@minimaxi.com>
|
2026-09-02 15:21:33 +08:00 |
|
|
Mick
|
9175590aa0
|
[diffusion] refactor: admit explicit attention backends by capability (#37441)
|
2026-09-02 15:17:57 +08:00 |
|
|
Lianmin Zheng
|
f8f04bafa8
|
Rust server: align launcher and request validation behavior (#37327)
|
2026-09-01 23:42:36 -07:00 |
|
|
jasonjk-park
|
83bd2c473f
|
Allow custom policy for adaptive speculative decoding (#37274)
|
2026-09-01 23:15:21 -07:00 |
|
|
Liangsheng Yin
|
01c3a5f54f
|
[misc] Resolve SWA ownership at enqueue time for grouped free() (#36646)
|
2026-09-01 23:06:55 -07:00 |
|
|
Liangsheng Yin
|
832d029870
|
[mem_cache] Split duplicate insert frees at the SWA eviction floor (#37481)
|
2026-09-01 23:01:40 -07:00 |
|
|
YAMY
|
a6a19f9290
|
[Bugfix] Skip absent radix lock during cache cleanup (#37494)
|
2026-09-01 22:50:19 -07:00 |
|
|
Khoa PhamandClaude Opus 5
|
c66a285c94
|
[Kernel] GLM 5.3 Flash related kernels (ported from #36507) (#37477)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-01 22:17:09 -07:00 |
|
|
KnightYao
|
a58751d54d
|
[Fix ] Fix Spark2.5 hybrid SWA config (#37335)
|
2026-09-01 20:29:09 -07:00 |
|
|
Wes
|
2d9c64394f
|
Fix reasoning metrics and add TPOT to bench_multiturn (#35443)
|
2026-09-02 11:28:47 +08:00 |
|
|
Xiaoyu Zhang
|
403a15c163
|
[CI] Batch CPU test workers (#37252)
|
2026-09-02 10:35:14 +08:00 |
|
|
Xiaoyu Zhang
|
1aa8299d1d
|
[Diffusion] Add cumulative extra-high quality tier (#37422)
|
2026-09-02 10:26:13 +08:00 |
|
|
|
26f760d5c0
|
[CPU] Support FP8 KV cache (#32733)
Co-authored-by: Zheng, Beilei <beilei.zheng@intel.com>
Co-authored-by: mingfeima <mingfei.ma@intel.com>
|
2026-09-02 10:20:54 +08:00 |
|
|
Yongji WuandLianmin Zheng
|
b83bf7a65f
|
[Bugfix] Avoid scanning crash-dump token buffers during GC (#37297)
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
|
2026-09-01 18:52:10 -07:00 |
|
|
Mick
|
22195709d1
|
[diffusion] refactor: remove component loader capability switches (#36824)
|
2026-09-02 09:48:50 +08:00 |
|
|
Yichao Fu
|
66de38f30c
|
Decouple ragged CUDA graph request and token capacities (#37300)
|
2026-09-01 18:48:11 -07:00 |
|
|
Mick
|
dde0ecdb90
|
[diffusion] feat: support spargeattention (#37437)
|
2026-09-02 09:42:33 +08:00 |
|
|
kkandwunhuang
|
dc276264cb
|
[AMD] Perf Kimi-K3 fuse ROCm KDA decode boundary (#34198)
Co-authored-by: wunhuang <wunhuang@amd.com>
|
2026-09-01 18:35:48 -07:00 |
|
|
|
8b596c10b0
|
[PD] Diversify fake-prefill handoff tokens (#37302)
Co-authored-by: xingyuliu <xingyuliu@fb.com>
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
|
2026-09-01 18:34:38 -07:00 |
|
|
Even Zhou
|
9cc43ca4e1
|
[NPU] Update sgl-kernel-npu version to 2026.9.0 and move memfabric deps into pyproject (#37399)
|
2026-09-02 08:57:59 +08:00 |
|
|
Xiaoyu ZhangandCursor
|
f4c17fed07
|
[Diffusion] Fuse FLUX.2 NVFP4 FC1, SwiGLU, and FC2 quantization (#37096)
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-09-02 08:21:14 +08:00 |
|
|
|
c593527f33
|
[Kernel] Add KDA NVFP4 GEMM for Qwen3.x on SM120 (#36865)
Co-authored-by: Song Bian <biansonghz@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-09-02 08:16:54 +08:00 |
|
|
|
33428d3dae
|
Fix GPU kernel ordering and MXFP8 quantization dispatch (#37331)
Co-authored-by: Pranjal Shankhdhar <pranjalssh@meta.com>
Co-authored-by: Chengze Fan <fancz2002@gmail.com>
|
2026-09-01 17:09:44 -07:00 |
|
|
YAMY
|
221a6273ce
|
[Kernel] Avoid zero-bias allocation in fused softmax routing (#36811)
|
2026-09-01 16:29:57 -07:00 |
|
|
Yikai Zhangandamdpilot-upstream-sync
|
9978aaec8b
|
[ROCm][Bugfix] Cap the DSA MQA-logits budget at AITER's buffer_store limit (#36960)
Co-authored-by: amdpilot-upstream-sync <amdpilot-upstream-sync@users.noreply.github.com>
|
2026-09-01 15:40:12 -07:00 |
|
|
|
f8618714c5
|
add reindex_device_id to device OOT plugin (#36220)
Co-authored-by: Akash Palla <apalla@fb.com>
Co-authored-by: Alex Nails <alex.nails@radixark.ai>
|
2026-09-01 15:26:47 -07:00 |
|
|
|
fb8d7eedda
|
Fix dummy initialization of inverse weight scales (#35491)
Co-authored-by: weireweire <20922698+weireweire@users.noreply.github.com>
Co-authored-by: Po-Han Huang (NVIDIA) <53919306+nvpohanh@users.noreply.github.com>
|
2026-09-01 14:19:14 -07:00 |
|
|
Po-Han Huang (NVIDIA)
|
e57e934bcc
|
[Bugfix] Accept int64 top-k IDs in FlashInfer routed MoE packer (#32882)
|
2026-09-01 14:17:46 -07:00 |
|
|
Liangsheng Yin
|
83a9b5dd88
|
[mem_cache] Drop the torch.unique sync from the SWA page expansion (#37463)
|
2026-09-01 14:16:47 -07:00 |
|
|
|
b24c8f10e7
|
[FlashInfer] Avoid D2H sync for sliding-window lengths (#32218)
Co-authored-by: llilian73 <204300658+llilian73@users.noreply.github.com>
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
|
2026-09-01 14:08:22 -07:00 |
|
|
Cheng Wan
|
0b1ce3d140
|
[Feature] Unified memory: support decode context parallelism for Kimi-Linear (#36890)
|
2026-09-01 12:44:26 -07:00 |
|
|
cctryandcctry
|
9a05b470fa
|
[Memory] Size the CUDA graph pool from warmup measurements and fix graph-pool borrowing (#36911)
Co-authored-by: cctry <cctry@fb.com>
|
2026-09-01 09:32:38 -07:00 |
|
|
|
c34f378342
|
fix(nixl): make FILE path-mode devId globally unique (#34362)
Co-authored-by: hekh <hekh@local>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-09-01 09:11:59 -07:00 |
|
|
Thomas Wang
|
bb3e3cbceb
|
[AMD] Fix v4 topk issue (#37439)
|
2026-09-01 08:37:30 -07:00 |
|
|
billishyahao
|
44a92e54b9
|
[AMD] fix aiter cannot get heuristic kernel regression (#37438)
|
2026-09-01 08:35:31 -07:00 |
|
|
DarkSharpnessandClaude Opus 5
|
cb6dd58fbe
|
[Kernel] Replace dsv3_router_gemm with the unified tiny GEMM (#34693)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-01 23:00:21 +08:00 |
|