iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
23,341 Commits 3 Branches 0 Tags
patches
Commit Graph
79 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Woosuk KwonClaude Opus 5.5vllm-agent
 		c0b6f74bee [Benchmark] Add per-case kernel profiles to vllm bench forward (#61692) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
 2026-10-17 08:27:11 -07:00
Woosuk KwonLainCodexClaude Opus 5.5vllm-agent
 		596e530675 [Kernel] Add router GEMM kernels for (5120, 256) and BF16 output to ll_bf16_gemm (#62042) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Lain <fusiyuan2000@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
 2026-10-16 15:39:46 -07:00
Woosuk KwonBugen ZhaoYoni GozlanneilkgCursorClaude Opus 5.5
 		153a17166e [Frontend] Add the Beam reasoning and tool parsers (#62052) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Yoni Gozlan <74535834+yonigozlan@users.noreply.github.com>
Co-authored-by: neilkg <33635204+neilkg@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-16 14:08:29 -07:00
Woosuk KwonandClaude Opus 5.5 4a89316efa [Core] Drop the Ray driver-node GPU pin left over from the legacy executor (#61713) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-15 16:00:18 -07:00
Woosuk KwonandClaude Opus 5.5 e57bb4ace7 [Core] Remove the legacy Ray compiled-graph executor (#61712) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-14 18:13:27 -07:00
Woosuk KwonandClaude Opus 5.5 8530aed2b7 [Spec Decode] Remove Medusa and MLP speculator support (#61701) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-14 17:29:23 -07:00
Woosuk KwonandClaude Opus 5.5 2e8a5930f6 [Benchmark] Remove the temporary bench forward dummy loader (#61676) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-14 13:30:18 -07:00
Woosuk KwonandClaude Opus 5.5 9d3dfa2886 [Benchmark] Add vllm bench forward: exact-shape forward timing (#61339) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-14 10:52:26 -07:00
Woosuk KwonandClaude Opus 5.5 ac71b17517 [Model Loader] Keep norm layers neutral under dummy weight init (#61323) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-13 08:54:24 -07:00
Woosuk KwonandClaude Opus 5.5 f47792af7f [Model Loader] Make dummy weight init dtype-aware (#61134) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-12 18:33:26 -07:00
Woosuk KwonandClaude Opus 5.5 e1a5086256 [Attention] Remove cascade attention (#61126) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-12 10:41:07 -07:00
Woosuk Kwon 194bd72be7 [Compile] Remove torch.compile-based sequence parallelism and AsyncTP (#60517) 2026-10-08 08:28:23 -07:00
Woosuk KwonandOpenAI Codex 67513c8b67 [Bugfix][DSV4.1] Restrict mHC overlap to full CUDA graphs (#57874) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>
 2026-09-21 01:16:59 -07:00
Woosuk KwonandOpenAI Codex 97dc6b19d2 [Perf][Attention] Avoid redundant sparse attention metadata operations (#57885) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>
 2026-09-21 00:08:43 -07:00
Woosuk KwonandCodex 9a70c233cd [Perf][DSV4.1] Fuse TP all-reduce with mHC input preparation (#57643) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
 2026-09-20 20:28:06 -07:00
Woosuk KwonandCodex 9b49f92344 [Perf][DSV4.1] Overlap mHC coefficients for small TP batches (#57603) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
 2026-09-20 17:33:17 -07:00
Woosuk Kwon c3b4844634 [Docs] Explain pointer-alignment JIT specialization in Triton skill (#57669) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-09-19 00:53:42 -07:00
Woosuk Kwon 38537331d3 [Bugfix][DSA] Avoid runtime JIT for offset candidate end buffers (#57667) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-09-19 00:27:11 -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
Woosuk KwonandCodex 64563d0ec4 [Bugfix][DSv4.1] Preserve NaN-scored candidate block indices (#57454) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
 2026-09-17 19:00:10 -07:00
Woosuk KwonandCodex 80447d2765 [Bugfix][DSv4.1] Fix FlashInfer DSpark non-causal attention (#57432) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
 2026-09-17 15:14:37 -07:00
Woosuk Kwon 30b847c1fa [Perf][DSV4.1] Remove MegaMoE padding and shared padding workaround (#57204) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-09-16 19:09:30 +00:00
Woosuk Kwon 3b533197a9 [Perf] Parallelize mHC pre-norm JIT warmup (#56683) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-09-13 18:58:20 -07:00
Woosuk KwonandOpenAI Codex 71888f507a [Perf] Avoid redundant conversions in FP8 dummy initialization (#56688) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>
 2026-09-13 12:06:13 -07:00
Woosuk Kwon e7a3963339 [Bugfix] Avoid repeated dummy initialization and random CPU Engram fills (#56682) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-09-13 02:23:20 -07:00
Woosuk KwonandOpenAI Codex 2671fedfc7 [MRV2] Revert explicit Triton JIT warmup migration (#56654) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
 2026-09-13 04:07:56 +00:00
Woosuk Kwon 13e221f830 [Perf] Fuse DSV4.1 input metadata preparation with Triton (#56562) 2026-09-12 07:20:04 -07:00
Woosuk Kwon 5f3e4b7447 Revert "[Agents] Link Triton skill to JIT kernel warmup guide" (#56546) 2026-09-11 20:15:02 -07:00
Woosuk KwonandOpenAI Codex 06334fae2d [Build] Remove obsolete TPU Dockerfile (#55376) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
 2026-09-07 18:07:27 -07:00
Woosuk Kwon 0e14198a63 [Skills] Add kernel benchmark sanity references (#54995) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-09-02 17:58:55 -07:00
Woosuk KwonandOpenAI Codex 443febe723 [Agents] Expose Triton kernel-writing skill to Claude (#55028) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
 2026-09-02 15:36:12 -07:00
Woosuk KwonandOpenAI Codex cf3263d571 [Agents] Add Triton kernel-writing skill (#55019) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
 2026-09-02 15:29:16 -07:00
Woosuk Kwon 0a5ad6f0d4 [Model] Remove unused DeepSeek V4 top-k buffer helper (#53697) 2026-08-26 11:59:09 -07:00
Woosuk KwonandOpenAI Codex c0233fcf01 [Model] Remove unused DeepseekV32Indexer forward (#53021) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
 2026-08-19 19:39:52 -07:00
Woosuk KwonandOpenAI Codex 6a962071bd [Distributed] Enable FlashInfer all-reduce by default (#52998) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
 2026-08-19 18:17:43 -07:00
Woosuk Kwon b09bd69b5b [Model][NVIDIA] Route DSA models to the CUDA non-compiled path (#52861) 2026-08-19 00:13:52 -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
Woosuk KwonandOpenAI Codex 01e56caaf2 [Bugfix][MLA] Do not use Dense MHA for GLM-5.2 (#52512) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
 2026-08-18 11:20:48 -07:00
Woosuk KwonBugen ZhaoOpenAI Codex
 		e0e5a7fb28 [Rust Frontend] Fix GLM-5.2 chat template rendering parity (#51426) 
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-08-18 03:16:54 +00:00
Woosuk KwonandOpenAI Codex 87668ab69b [Bugfix] Guard DeepSeek V4 MRV1 piecewise CUDA graphs (#51768) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
 2026-08-11 07:34:44 -07:00
Woosuk KwonandOpenAI Codex 79c865b838 [Perf] Narrow DeepSeek V4 eager CUDA graph region (#51430) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
 2026-08-10 10:52:10 -07:00
Woosuk Kwon e644c8cd8c [Perf] Optimize DeepSeek V3.2 sequence parallelism (#51434) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-08-07 16:51:01 -07:00
Woosuk Kwon 46b5864054 [Perf] Narrow DeepSeek V3.2 eager CUDA graph region (#51425) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-08-07 14:37:43 -07:00
Woosuk Kwon 38a466e7b6 [DSV4] Implement Sequence Parallelism (#46789) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-08-01 10:22:33 -07:00
Bugen Zhao 2899dca843 [Model] Add Kimi K3 support: Rust frontend [1/2] (#50104) 
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
 2026-07-28 14:31:13 -07:00
Woosuk Kwon 60b3d39cd3 [Docs] Remove experimental warning for EP (#50057) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-07-27 17:06:28 -07:00
Woosuk Kwon 213f681f81 Revert "[Perf][GLM-5.2] Blackwell decode optimizations" (#49768) 2026-07-24 16:04:59 -07:00
Woosuk Kwon 6049424b7e [MRV2] Always build attn metadata at capture time (#49364) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-07-21 19:27:16 -07:00
Woosuk KwonBugen ZhaoGiancarlo DelfinIsotr0pyIsotr0pyJee Jee LiRoger WangYifan QiaoClaude Fable 5OpenAI Codex
 		ee8f36d0b3 [Warmup] Show CuTeDSL compilation progress (#48881) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Giancarlo Delfin <32987265+TheEpicDolphin@users.noreply.github.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Isotr0py <mozf@inferact.ai>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
 2026-07-16 20:17:51 -07:00
Woosuk KwonBugen ZhaoGiancarlo DelfinIsotr0pyIsotr0pyJee Jee LiRoger WangYifan QiaoClaude Fable 5OpenAI Codex
 		f3e9497e92 [Model] Add Inkling LoRA support [4/N] (#48884) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Giancarlo Delfin <32987265+TheEpicDolphin@users.noreply.github.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Isotr0py <mozf@inferact.ai>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
 2026-07-17 09:52:15 +08:00
Woosuk KwonBugen ZhaoGiancarlo DelfinIsotr0pyIsotr0pyJee Jee LiRoger WangYifan QiaoClaude Fable 5OpenAI Codex
 		fb5ec0dc9e [Model] Add Inkling MTP=1 support [3/N] (#48869) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Giancarlo Delfin <32987265+TheEpicDolphin@users.noreply.github.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Isotr0py <mozf@inferact.ai>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
 2026-07-16 13:27:21 -07:00
Woosuk Kwon f61163e6c7 [Model] Add Hopper FA4 relative attention for Inkling (#48858) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-07-16 11:26:52 -07:00
Woosuk KwonBugen ZhaoGiancarlo DelfinIsotr0pyIsotr0pyJee Jee LiRoger WangYifan QiaoClaude Fable 5OpenAI Codex
 		251f7e478e [Model] Add PW CUDA graph support for Inkling [2/N] (#48822) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Giancarlo Delfin <32987265+TheEpicDolphin@users.noreply.github.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Isotr0py <mozf@inferact.ai>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
 2026-07-16 10:28:56 -07:00
Woosuk KwonBugen ZhaoGiancarlo DelfinIsotr0pyIsotr0pyJee Jee LiRoger WangYifan QiaoClaude Fable 5OpenAI Codex
 		6570c9800c [Model] Add Inkling model support [1/N] (#48799) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Giancarlo Delfin <32987265+TheEpicDolphin@users.noreply.github.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Isotr0py <mozf@inferact.ai>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
 2026-07-15 23:40:07 -07:00
Woosuk KwonClaude Fable 5Nick Hill
 		85b3a7264b [Bugfix][Model Runner V2] Order uniform decodes first so spec decodes aren't misclassified as prefills (#47381) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
 2026-07-09 14:26:27 +01:00
Woosuk KwonandClaude Fable 5 a47f38f825 [Bugfix][Model Runner V2][Spec Decode] Fix int32 offset overflow in block verification kernels (#47383) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-02 07:32:38 -07:00
Woosuk KwonandClaude Opus 4.8 a264e41975 [Distributed] Default FlashInfer allreduce to mnnvl on single node (#47219) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-30 18:35:56 -07:00
Woosuk Kwon 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
Woosuk Kwonandsnordmann 953bba488d [PERF] Extend NCCL symmetric memory to AllGather and ReduceScatter (#46703) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: snordmann <snordmann@nvidia.com>
 2026-06-30 11:38:18 -07:00
Woosuk Kwon a309d4fe60 Support DCP with FlashInfer MLA (#43729) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-06-29 13:24:29 -07:00
Woosuk Kwon 0472436541 [Spec Decode] Avoid redundant hidden-states gather in draft prefill (#46968) 2026-06-28 17:04:01 -07:00
Woosuk Kwon 4b643c463e [GLM5] Fix minor typo (#46961) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-06-28 08:37:00 -07:00
Woosuk Kwon 89876b0c54 [GLM5] Implement op fusion for GLM5/DSV3.2 (#46876) 2026-06-28 08:17:39 -07:00
Woosuk Kwon 65e655d295 [GLM-5] Add DSV3.2/GLM5 to vllm/models/ (#46808) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-06-26 14:09:05 -07:00
Woosuk KwonandClaude d7ab9be775 [Bugfix] Support -1 (invalid/non-local) slots in topk_ids for Triton MoE (#46408) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-06-24 13:59:42 -07:00
Woosuk KwonandClaude 6a1570711c [Bugfix] Support non-power-of-2 top_k in legacy triton_kernels routing (#46406) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-06-24 13:52:09 -07:00
Woosuk Kwon 96de8bb389 [MoE] Free unused MXFP4 scales in OAI Triton Backend (#46549) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-06-24 00:06:41 -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
Woosuk Kwon 04c2a8deac [DeepEP V2] Fill invalid recv_topk_idx with -1 (#46432) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-06-22 21:45:49 -07:00
Woosuk KwonRoy WanggnovackClaudemergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 		e48592066e [DeepEP V2] Bound num_max_tokens_per_rank in do_expand=False (#46404) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Roy Wang <jasonailu87@gmail.com>
Co-authored-by: gnovack <novackgm@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-06-22 18:14:53 -07:00
Woosuk Kwon 16908e132e [MRV2] Make FP32 Gumbel sampling more accurate (#45996) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-06-18 19:42:09 +00:00
Woosuk KwonandClaude Opus 4.8 1797576237 Revert "[DSV4 Perf] Optimize dsv4 cudagraph by reducing eager_break_during_capture" (#45309) (#45972) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-17 17:20:59 -07:00
Woosuk Kwon f4359a70f9 [DSV4][Minor] Fix supported KV cache dtypes (#44892) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-06-16 00:14:51 +00:00
Woosuk Kwon 2a983c79ac [DSV4] Decouple DS V4 Sparse MLA Metadata from DS V3.2 (#44699) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-06-06 20:37:56 -04:00
Woosuk Kwon 02d2da0748 [DSV4] Move more ops out of eager breakpoint (#44561) 2026-06-05 06:42:41 -07:00
Woosuk Kwon 4efd6ffde0 [DSV4] Refactor DeepseekV4Attention (#44569) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-06-04 20:23:07 -07:00
Woosuk Kwon 6bad553f4e [Minor] Remove FlashInfer version check in topk_topp_sampler (#44442) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-06-03 21:06:00 +00:00
Woosuk Kwon b254e0456c [DSV4] Minor cleanup for DeepseekV4MegaMoEExperts (#44367) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-06-02 17:54:27 -07:00
Woosuk Kwon e4a2e584e5 [MRV2] Remove assignment of graph_pool in cudagraph_utils (#44338) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-06-02 11:50:27 -07:00