32 Commits
Author SHA1 Message Date
f8460ef236 [Kernel][DSv4.1] Bump FlashMLA to the 2026.09.30 release and its interleaved V4.1 KV cache (#61371)
Signed-off-by: juntianl <juntianl@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Kimi Code <noreply@moonshot.ai>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
2026-10-15 13:58:25 -07:00
4d58fa254a [MoE] Unify DeepGEMM MegaMoE experts behind one feature-matrix layer; add NVFP4 (#61538)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
2026-10-15 19:02:01 +00:00
Harry MellorClaude Opus 5.5mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>Kevin H. Luu
b965ee564d [Chore] Use upstream Transformers DeepseekV4Config (#61392)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
2026-10-15 01:08:08 -07:00
81198e97ba [Refactor] Abstract DeepGemm MegaMOE backend (#58053)
Signed-off-by: Hui Shi <kalinshi@tencent.com>
Co-authored-by: LuneExplorer <liyihan23@mails.tsinghua.edu.cn>
Co-authored-by: ArmageddonKnight <bojian@cs.toronto.edu>
2026-10-08 05:05:39 +00:00
Yongye ZhuandClaude Opus 5.5 5ff3bbfb08 [Perf][DSv4] Fuse inverse RoPE + FP8 quant into FlashInfer sparse MLA (#58621)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-24 23:26:50 -07:00
f92b78f6ef [Kernel][DSV4.1] Fuse MXFP8 wo_b GEMM with sequence-parallel reduce-scatter (#57428)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Signed-off-by: Canlin <canlinguosdu@gmail.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
2026-09-22 01:07:17 -07:00
Woosuk KwonandCodex 50d812b66a [Perf][DSV4.1] Optimize MegaMoE staging and NVFP4 cache gathers (#57604)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
2026-09-18 12:57:19 -07:00
Jared WenandClaude Fable 5.1 1257512305 [DSA] Wire DeepGEMM sparse MQA logits into the DeepSeek V4.1 indexer (#56254)
Signed-off-by: Jared Wen <w13431838023@gmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-15 14:07:14 -07:00
e6eb0d120c [Model][DSv4.1] Store the whole KV in MXFP8 (FlashMLA V4.1 record) (#56893)
Signed-off-by: Yongye Zhu <yongye@inferact.ai>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Yongye Zhu <yongye@inferact.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-14 20:12:55 -07:00
Roberto L. Castro c377114636 [Bugfix][CI] Update CuTeDSL indexer Q sentinel test for migrated wrappers (#56594)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
2026-09-12 09:12:58 -07:00
Roberto L. CastroandCodex 120ec4ebd2 [5/N][warmup][DSv4] Migrate NVIDIA CuTeDSL attention kernels (#53566)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Co-authored-by: Codex <codex@openai.com>
2026-09-12 00:05:59 -04:00
9b959b8657 [Model] DeepSeek-V4.1-Flash Model Definitions (#56228)
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Kimi Code <noreply@moonshot.cn>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-10 20:16:26 +08:00
aoshen02andaoshen02 69cf055936 [Performance][DSv4] Size dequant gather launch grid by rows (#55061)
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: aoshen02 <aoshen524@gmail.com>
2026-09-03 20:06:34 -07:00
Canlin Guo 4f6885fffc [DSV4][Kernel] Fuse shared experts into MegaMoE (#53040)
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
2026-08-20 12:07:02 -07:00
Woosuk KwonandOpenAI Codex f1178f3a06 Revert DSv4 eager workspace reuse (#52836)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-08-18 17:02:59 -07:00
Wentao Yeandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> df71917cf1 [DSv4 Perf] Optimize workspace reuse for eager break, 3.9% E2E TTFT improvement. (#49236)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-07-31 08:45:58 -07:00
Kyle Sayers bf27e34ebb [CompressedTensors] DeepSeek4 CT Quantization Support (#41276)
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
2026-07-23 20:07:31 -07:00
Woosuk Kwonandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 0a3e2dbc09 [Optimization] Skip DP padding tokens in MoE (#46428)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-06-23 14:54:46 -07:00
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
Woosuk Kwon 4efd6ffde0 [DSV4] Refactor DeepseekV4Attention (#44569)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
2026-06-04 20:23:07 -07:00
Yongye Zhu b5235fca2e [DSv4] Adding TRTLLM gen attention kernel (#43827) 2026-06-04 07:35:09 -07:00
Jie FangandYongye Zhu f0cd590d62 optimize the compressor 128 split cutedsl kernel (#44230)
Signed-off-by: Jie Fang <jief@nvidia.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
2026-06-03 20:22:57 -07:00
Willow Lopez 597bc15936 fix: resolve CUTLASS fmin compatibility for DeepSeek-V4 init (#44236)
Signed-off-by: Willow Lopez <100782273+Oxygen56@users.noreply.github.com>
2026-06-03 01:07:10 -04:00
Yongye Zhu 035733515f [Kernel][DSv4] Optimize sparse FP8 compressor kernels (#44161)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
2026-06-02 00:18:32 +08:00
Harry Mellor 41688e2dc7 Fix early CUDA init (#43791)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2026-05-27 09:30:11 -07:00
Woosuk Kwon adaa5e455a [DSv4] Refactor compressor & Fix ROCm compatibility (#43710)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
2026-05-26 19:56:46 -07:00
Yongye Zhu 6ab6ffb428 [Feat][DSV4] Fuse q pad into deepseek v4 fused kernel (#43162) 2026-05-26 05:12:54 -10:00
Thien Tran d56612c621 [GDN] GDN Prefill kernel for SM100 (#43273)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
2026-05-26 14:02:11 +08:00
Woosuk Kwon aa2b56ffb0 [DeepSeek V4] Move MegaMoE input prep kernel to nvidia/ops (#43632)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
2026-05-25 21:08:29 -07:00
Yongye Zhu 367cb81966 [DSV4] More multi-stream enablement for c4a (#42925)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
2026-05-23 09:22:27 +08:00
Yongye Zhu 843715739b [Refactor] Extract DeepSeek V4 sparse MLA impl into model folder (#43149) 2026-05-22 10:06:31 -07:00
Woosuk Kwon b14be81c1f [Model Refactoring] Move deepseek_v4_ops to models/deepseek_v4 [3/N] (#43073)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
2026-05-19 00:52:54 -07:00