Commit Graph
146 Commits
Author SHA1 Message Date
9654e5c4bc dsv4.1-amd: fused mHC boundary and all-reduce + mHC post kernels (#41021)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Kevin Mi <kevin.mi@radixark.ai>
2026-09-28 16:15:08 -07:00
triple-mu 2e7e0802f4 [diffusion] Qwen-Image 2.1: fuse Q/K RMSNorm + RoPE + KV packing into one CUDA kernel and project Q/K/V with one packed GEMM (#41339) 2026-09-28 21:45:39 +08:00
DarkSharpnessandClaude Opus 5.5 8151378c1a [DeepSelect] Add page-table transform to top-k and tighten the layout contract (#41364)
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-28 21:43:57 +08:00
e581520c67 [HiCache] Add the page-unified KV load-back JIT kernel (#39726)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: huangtingwei <141888744+huangtingwei9988@users.noreply.github.com>
Co-authored-by: Zhangheng <hzh0425@apache.org>
2026-09-28 01:45:02 +08:00
Kevin Miandx effb752188 dsv4.1-amd: KV cache layouts, FP4 indexer, compressor and router kernels (#41019)
Co-authored-by: x <x>
2026-09-26 19:44:47 -07:00
Thomas Wang c73f7077eb [AMD] Fix jit broken on rocm env (#41356) 2026-09-26 09:59:59 -07:00
Mohammad Miadh AngkadandMohammad Angkad cdbea5dccf [CI] Move DeepSelect into the attention kernel group to fix the namespace test (#41349)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-26 21:39:00 +08:00
7bc988446d [DeepSeek V4.1] Add DeepSelect JIT kernel. (#40556)
Co-authored-by: DarkSharpness <2040703891@qq.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-26 17:36:48 +08:00
Xiaoyu Zhang 38ec649048 [Refactor] Restore logical kernel groups and test organization (#41243) 2026-09-26 12:30:44 +08:00
Kevin MiandClaude Opus 5.5 27e883a20d dsv4.1-amd: gfx950 MXFP8 matmul kernels and fp8-grid producers (#41018)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-25 15:45:40 -07:00
Xiaoyu Zhang c85df5becc [Diffusion] Fuse lossless Wan VAE post-ops for LongLive 2 I2V (#40405) 2026-09-24 17:40:07 +08:00
Xiaoyu Zhang 261cb826e6 [Diffusion] Fuse LongCat GELU+cat and support Edit-Turbo BCG (#40384) 2026-09-24 17:27:56 +08:00
f2a1366584 MiniMax-M3: wave64 histogram-select decode top-k, and raise kMaxNumBlocks for CUDA graphs (#36560)
Co-authored-by: Kevin Mi <mikevin920@yahoo.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Kevin Mi <mikevin920@gmail.com>
Co-authored-by: Kevin Mi <45493463+kevin-mii@users.noreply.github.com>
Co-authored-by: YC Yen-Ching Tseng <yctseng@amd.com>
2026-09-23 14:50:13 -07:00
2909f84e3b [JIT] Add an occupancy-preserving L1 carveout preference (#40767)
Co-authored-by: metamergebot <324680979+metamergebot@users.noreply.github.com>
Co-authored-by: Oguz Ulgen <oulgen7@gmail.com>
2026-09-23 11:49:34 -07:00
Guangda LiuandGuangda Liu 04c0913434 [HiSparse] Add MHA hisparse support for MiniMax M3 (#31446)
Co-authored-by: Guangda Liu <bingps@users.noreply.github.com>
2026-09-22 13:28:03 +08:00
8bde82c0ad [AMD] [GLM-5.3-Flash Day 0] Build the fused DSA k-pool top-k JIT kernel on HIP (#39339)
Co-authored-by: Raiden-Makoto <Raiden-Makoto@users.noreply.github.com>
Co-authored-by: Thomas Wang <thomawan@amd.com>
Co-authored-by: Kevin Mi <mikevin920@yahoo.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-21 15:24:44 -07:00
cctry 7ad55e4386 [HiCache] TMA-staged host<->device KV transfer kernel (sm_90+) (#40278) 2026-09-21 10:38:23 -07:00
Eric.Chin.AMDandThomas Wang 3c71bb018a [AMD] Enable GLM DSA prefill top-k to the v2 kernel (#37889)
Co-authored-by: Thomas Wang <thomawan@amd.com>
2026-09-21 10:31:07 -07:00
luoroger37andHank Han d97aed2c90 Fix TopK v2 fallback when 16-block cluster capacity is zero (#40163)
Co-authored-by: Hank Han <hanhan7630@outlook.com>
2026-09-21 06:41:41 +08:00
993d1fccba [ROCm] Widen the HiCache JIT copy rounds and enable the K-only host pool (#37152)
Co-authored-by: Xiaobo Chen <xiaobche@smci355-ccs-aus-n05-33.prov.aus.ccs.cpe.ice.amd.com>
Co-authored-by: HAI <hixiao@gmail.com>
2026-09-19 08:58:10 -07:00
Xiaoyu Zhang 7fac84b639 [DSV4.1] Reduce mHC, metadata and small-batch router overhead (#39704) 2026-09-19 19:51:21 +08:00
DarkSharpnessandBBuf d1acbe0746 [DSV4.1] Big fused wo_a quant (#39957)
Co-authored-by: BBuf <1182563586@qq.com>
2026-09-19 19:46:53 +08:00
Xiaoyu Zhang 0b0d2c257a [Fix] Repair CI fixtures and ROCm speculative tree device checks (#40325) 2026-09-19 18:16:05 +08:00
Xiaoyu Zhang 986959e3c4 [Refactor] Deduplicate kernel helpers and remove unused code (#40197) 2026-09-19 09:27:30 +08:00
0e5347db82 Support MXFP8 and deferred route weighting in DeepEP v2 (#40030)
Co-authored-by: metamergebot <324680979+metamergebot@users.noreply.github.com>
Co-authored-by: Xingyu Liu <38244988+charlotte12l@users.noreply.github.com>
Co-authored-by: pranjalssh <14260275+pranjalssh@users.noreply.github.com>
2026-09-18 15:40:38 -07:00
81363bf8cb [kernel] Share the warp vectorized copy and enforce its alignment (#36176)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: BBuf <1182563586@qq.com>
2026-09-18 22:40:54 +08:00
Nan Jiang 740f57a02c [Spec] Fix CDF boundary handling in TreeSpeculativeSamplingTargetOnly (#35798) 2026-09-17 19:41:52 -07:00
Liangsheng Yin f65c70bb7d [Kernel] Move CUDA and ROCm speculative kernels to JIT (#40033) 2026-09-17 17:27:26 -07:00
William Hu 0443e3179f fix(kda_prefill): fence shared writes before async proxy reads (#39124) 2026-09-16 18:37:19 -07:00
Xinyi Song 7780882f18 [AMD][bugfix] Fix dsv4 server launch (#39875) 2026-09-16 18:28:02 -07:00
c2443458e1 dsv4.1: RoPE and FP4 packing kernels (#39656)
Co-authored-by: DarkSharpness <2040703891@qq.com>
Co-authored-by: Xiaoyu Zhang <1182563586@qq.com>
Co-authored-by: BBuf <1182563586@qq.com>
2026-09-16 16:17:12 -07:00
13d593b6cf dsv4.1: compression, KV I/O, and metadata kernels (#39652)
Co-authored-by: BBuf <1182563586@qq.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: DarkSharpness <76582120+DarkSharpness@users.noreply.github.com>
2026-09-16 13:54:07 -07:00
cctry 1b78083b42 [PD] Add optional KV transfer checksums (#39500) 2026-09-16 23:53:30 +08:00
+4 7d5696b3a1 dsv4.1: communication kernels and wrappers (#39653)
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: DarkSharpness <2040703891@qq.com>
Co-authored-by: DarkSharpness <76582120+DarkSharpness@users.noreply.github.com>
Co-authored-by: Ke Bao <ispobaoke@gmail.com>
Co-authored-by: Khoa Pham <khoa.pham@radixark.ai>
Co-authored-by: Xiaoyu Zhang <1182563586@qq.com>
Co-authored-by: Xiaoyu Zhang <xiaoyu.zhang@radixark.ai>
Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com>
Co-authored-by: Yuwei An <ayw.sirius19@gmail.com>
Co-authored-by: Zhichen Zeng <zczeng@uw.edu>
Co-authored-by: Ziyi Xu <ziyi.xu@radixark.ai>
2026-09-16 02:09:40 -07:00
+4 faaff1eca8 dsv4.1: Top-k kernels and candidate selection (#39648)
Co-authored-by: BBuf <1182563586@qq.com>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: DarkSharpness <2040703891@qq.com>
Co-authored-by: DarkSharpness <76582120+DarkSharpness@users.noreply.github.com>
Co-authored-by: Ke Bao <ispobaoke@gmail.com>
Co-authored-by: Khoa Pham <khoa.pham@radixark.ai>
Co-authored-by: Xiaoyu Zhang <1182563586@qq.com>
Co-authored-by: Xiaoyu Zhang <xiaoyu.zhang@radixark.ai>
Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com>
Co-authored-by: Yuwei An <ayw.sirius19@gmail.com>
Co-authored-by: Zhichen Zeng <zczeng@uw.edu>
Co-authored-by: Ziyi Xu <ziyi.xu@radixark.ai>
2026-09-15 23:54:35 -07:00
Liangsheng Yin 91f691c490 dsv4.1: standalone kernels and Python wrappers (#39646) 2026-09-15 22:31:18 -07:00
AMD-yanfeiwang 0163f8ff74 [AMD] Fix registered HiCache host pointer aliases (#35233) 2026-09-14 15:49:05 -07:00
Aurick QiaoandAurick Qiao 2123aca87e [Fix] Wait for PDL before reading DeepSeek V4 K cache locations (#38409)
Co-authored-by: Aurick Qiao <6137920+aurickq@users.noreply.github.com>
2026-09-14 21:04:28 +08:00
amd-danli103 5aa9b8fb3e [AMD][DSV4] feat: enable fp8 two-pool unified_kv on gfx950 (#37413) 2026-09-14 02:49:11 -07:00
cebca698e2 [Qwen3.8] Enable NVIDIA NVFP4 on DGX Spark with file-backed PLE and PDL router fix (#39126)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: rdxa <rdxa@rdxa-int-spark-01.yvb.moe>
Co-authored-by: Yangmin Li <yangminl@nvidia.com>
Co-authored-by: Manrique <nanomlm@gmail.com>
Co-authored-by: yhyang201 <yhyang201@gmail.com>
2026-09-13 16:23:41 +08:00
Xiaoyu ZhangandMick Qian 3e035a3513 [Diffusion] Optimize Qwen-Image-Edit attention on Hopper (#38584)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
2026-09-13 09:15:01 +08:00
Qiaolin Yu 6953dae005 [Qwen 3.8 Next] Remove unused tokenwise QSA implementation and tests (#38960) 2026-09-12 01:32:01 -07:00
ff1ce11348 [diffusion] model: support VDN-H3 with a hybrid_window_attn_h3 backend (#37903)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Haocheng Xi <xihc@berkeley.edu>
Co-authored-by: Mick <mickjagger19@icloud.com>
2026-09-12 11:36:32 +08:00
335f6aab27 [DSV4] Support raw-index output in TopK v2 (#33672)
Co-authored-by: weireweire <20922698+weireweire@users.noreply.github.com>
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
Co-authored-by: Po-Han Huang (NVIDIA) <53919306+nvpohanh@users.noreply.github.com>
2026-09-11 07:17:36 -07:00
MickandMick Qian 358c163250 [diffusion] fix: recover ipc jit initialization after interrupted builds (#39034)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
2026-09-11 19:34:09 +08:00
Mohammad Miadh AngkadandMohammad Angkad 52c191da52 [Deps] Retire the CUDA 12 lane (#38404)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-10 16:58:09 -07:00
Mohammad Miadh AngkadandMohammad Angkad dc2157dcd6 [JIT] Port the expert-pack MXFP4 kernels to load_jit and fix their launch limits (#38830)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-10 17:50:51 +08:00
Brayden ZhongandBrayden Zhong 7152c14384 Fix DeepSeek-V4 routing: sqrtsoftplus underflow and unfloored renorm (#34459)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
2026-09-10 15:10:50 +08:00
Mohammad Miadh AngkadandMohammad Angkad 72d5c5bb73 [Kimi-K3] Accept fp32 routing weights in the fused MoE finalize (#38612)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-09 01:33:39 -07:00
+3 52fecfdf09 support qwen 3.8 flash next (#37500)
Co-authored-by: ch-wan <54331508+ch-wan@users.noreply.github.com>
Co-authored-by: ispobock <26454835+ispobock@users.noreply.github.com>
Co-authored-by: JustinTong0323 <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: samuellees <26428561+samuellees@users.noreply.github.com>
Co-authored-by: YAMY1234 <74099316+YAMY1234@users.noreply.github.com>
Co-authored-by: yhyang201 <47235274+yhyang201@users.noreply.github.com>
Co-authored-by: yizhang2077 <25844240+yizhang2077@users.noreply.github.com>
Co-authored-by: zijiexia <37504505+zijiexia@users.noreply.github.com>
Co-authored-by: Shinto C V <cshintov@gmail.com>
Co-authored-by: Julian Huang <huangzhilin.hzl@antgroup.com>
Co-authored-by: Xiaoyu Zhang <1182563586@qq.com>
Co-authored-by: yhyang201 <yhyang201@gmail.com>
2026-09-08 13:56:21 -07:00