karylab_agents/vllm
1
0
Fork 0
forked from Karylab-cklius/vllm
Code Pull Requests 2 Actions 1 Packages Activity
15,002 Commits 354 Branches 175 Tags
eadf848ea00860e583da3a7da17ff113ad2ca267
Commit Graph
149 Commits
Author SHA1 Message Date
Tyler Michael SmithandClaude Opus 4.6 0d98729a49 [Kernel] Add zero-cost NaN/Inf detection to RMSNorm kernels 
Add per-token NaN/Inf detection to all RMSNorm CUDA kernels by
piggybacking on the existing variance reduction. NaN/Inf propagates
through sum-of-squares naturally, so a single isnan(variance) ||
isinf(variance) check on thread 0 after the CUB reduction detects
it -- zero additional kernel launches, memory reads, or register
pressure. Each block writes to its own int8 flag slot (no atomics).

Controlled by VLLM_NAN_DETECT=1. When enabled:
- Bypasses Oink/batch-invariant paths (with warning)
- Reports per-token, per-layer NaN/Inf with layer names
- Distinguishes real-token errors from padding-token warnings
- CUDA-graph compatible (fixed flag buffer address)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
 2026-03-28 13:12:28 -04:00
Michael GoinandGitHub 09e4576f65 [Kernel] Add non-gated support for NVFP4 CUTLASS MoE (#37320) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2026-03-17 18:12:04 -04:00
Terry GaoandGitHub 3e6a1e1686 [Custom Ops] Add functional + out variant for scaled_fp4_quant (#34389) 
Signed-off-by: tianrengao <terrygao87@gmail.com>
 2026-03-16 18:51:46 -04:00
Roberto L. CastroandGitHub 580864d81e [Attention][Perf][Kernel] Replace torch.cat with vectorized CUDA kernel MLA query concat - DeepSeek-V3.2 (#34917) 
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
 2026-03-09 09:50:36 -07:00
EdalatiAliGitHubMichael Goin
 		cb21972a97 [Kernel] Integrate SM100 MXFP8 blockscaled grouped MM and quant kernels (#34448) 
Signed-off-by: EdalatiAli <aliedalati@cohere.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2026-03-01 23:31:19 -08:00
Asaf GardinandGitHub bbf81f9a92 [Mamba1] - Kernel Level Chunk Alignment for Prefix Caching (#34798) 
Signed-off-by: Josephasafg <ajgard7@gmail.com>
 2026-03-01 20:40:23 +08:00
Tyler Michael SmithGitHubClaude Opus 4.6
 		eb19955c37 [WideEP] Remove pplx all2all backend (#33724) 
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-26 14:30:10 -08:00
Michael GoinandGitHub 3ef9fd0f98 [Bugfix] Fix DSV3 kernels breaking _C and _moe_C on unsupported arches (#35123) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2026-02-23 17:11:27 -08:00
Robert ShawGitHubRobert Shaw
 		6874638bc4 [Model Bash] DeepSeek R1 BF16 Min Latency QKV A GEMM (0.5% E2E Speedup) (#34758) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
 2026-02-18 07:42:36 -08:00
ElizaWszolaGitHubLuka Govedič
 		a88b3be7c4 [Bugfix] Fix quant RMS norm fusion for quantization with TMA-aligned scales (#33255) 
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
 2026-02-17 23:35:04 -08:00
Roberto L. CastroGitHubClaude Sonnet 4.5
 		afdce12c89 [Perf][Kernel] Add faster topKperRow decode kernel for DeepSeek-V3.2 sparse attention (#33680) 
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-10 10:29:52 -05:00
Robert ShawGitHubRobert ShawHarry Mellor
 		af9b69f977 [Quantization][Deprecation] Remove Marlin 24 (#32688) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-01-28 15:54:59 +00:00
Roberto L. CastroandGitHub fcb9df99bd [Perf][Kernel] Optimize FP4 quantization kernels (SM100F) (#32520) 
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
 2026-01-24 18:45:27 -07:00
Michael GoinandGitHub 4561f13985 [Refactor] Rename gptq_marlin to marlin to match MoE (#32952) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2026-01-23 16:48:12 -05:00
Or OzeriandGitHub 421012b63a OffloadingConnector: Support kernel_block_size != block_size (#30692) 
Signed-off-by: Or Ozeri <oro@il.ibm.com>
 2026-01-22 12:30:04 +00:00
Wentao YeandGitHub eebc58df0c [Refactor] Remove unused cutlass moe problem size function (#32047) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-01-18 12:46:59 -08:00
PatrykSafferGitHubPatryk SafferLuka GovedičMichael Goin
 		80fead8bf6 Fuse RoPE and MLA KV-cache write (#25774) 
Signed-off-by: Patryk Saffer <patryk.saffer99@gmail.com>
Signed-off-by: PatrykSaffer <patryk.saffer@mistral.ai>
Co-authored-by: Patryk Saffer <patryk.saffer99@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2026-01-09 19:18:37 -08:00
Lucas WilkinsonandGitHub 0a0aa07747 [Quant] Make static quant support all group shapes (#30833) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2026-01-09 12:49:27 -08:00
Wentao YeGitHubLuka Govedič
 		308feab33f [Perf] Optimize cutlass moe problem size calculation, 5.3% E2E Throughput improvement, 2.2% TTFT improvement (#31830) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
 2026-01-09 11:13:43 -08:00
Michael GoinandGitHub 34cd32fe30 [Perf][Kernel] Fused SiLU+Mul+Quant kernel for NVFP4 cutlass_moe (#31832) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
 2026-01-09 07:40:33 -07:00
rongfu.lengandGitHub 4ed11105d7 [Misc] Remove unused custom ops copy_blocks and copy_blocks_mla (#30967) 
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
 2025-12-23 18:22:35 -08:00
Robert ShawGitHubRobert Shaw
 		83a317f650 [MoE Refactor][3/N] Deprecate cutlass block quant fp8 (b200) (#30990) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
 2025-12-19 13:09:54 -08:00
Lucas WilkinsonandGitHub 3e41992fec [Attention] Use sparse prefill kernel for fp8 kv-cache in DeepSeek-v3.2 (#27532) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-12-12 05:57:47 -08:00
czhu-cohereandGitHub f6227c22ab [Kernel]Support W4A8 Grouped GEMM on Hopper (#29691) 
Signed-off-by: czhu-cohere <conway.zhu@cohere.com>
 2025-12-08 19:29:06 -08:00
Daniel CámporaGitHubMichael GoinCyrus Leung
 		184076c3fe [DeepSeek v3.2] Make top-k work for any logit values. (#27568) 
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2025-12-08 06:55:58 -08:00
ElizaWszolaGitHubyewentao256
 		af0444bf40 [Performance] Fused blockwise quant RMS norm (#27883) 
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
 2025-12-07 16:38:04 +00:00
Wentao YeandGitHub 541a2ef892 [Perf] Deepgemm fused layout kernel for activations, 4.3% throughput improvement, 10.7% TTFT improvement. (#29546) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-12-07 20:31:14 +08:00
Jinzhen LinGitHubMichael GoinMichael Goin
 		1656ad3704 [Kernel][Quantization] add w4a8 support for marlin kernel (#24722) 
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin@redhat.com>
 2025-11-29 07:19:33 -08:00
PleaplusoneandGitHub d9d342d214 [Performance][MLA][ROCm] Remove redundant D2D copy in deepseek (#27457) 
Signed-off-by: ganyi <ygan@amd.com>
 2025-11-26 12:45:28 +08:00
PleaplusoneandGitHub 77e10c9cab [Perf][Deepseek] optimize gather_and_maybe_dequant_cache kernel's perf for extremely long sequence (#28029) 
Signed-off-by: ganyi <ygan@amd.com>
 2025-11-24 19:05:46 -07:00
Boyuan FengGitHubCyrus Leung
 		a903d59ffa cleanup at::Tag::needs_fixed_stride_order (#28974) 
Signed-off-by: Boyuan Feng <boyuan@meta.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2025-11-20 02:51:36 -08:00
TJianandGitHub edb59a9470 [ROCm] [Bugfix] Fix fused_qknorm_rope_kernel rocm compatibility (#28500) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-11-12 05:01:14 -08:00
zhrrrandGitHub 68c09efc37 [Kernel][Perf] fuse QK Norm and RoPE into one cuda kernel for Qwen Model (#27165) 
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
 2025-11-11 12:00:31 -05:00
Asaf Joseph GardinandGitHub 00b31a36a2 [V1] [Hybrid] Mamba1 Automatic Prefix Caching (#26377) 
Signed-off-by: asafg <39553475+Josephasafg@users.noreply.github.com>
 2025-11-02 04:16:23 -08:00
Xiangyu LiandGitHub 5cc6bddb6e [Kernel] Add GPTQv2 format support for low-bit or asymmetric quantization, by adapting gptq_gemm (#26092) 2025-10-23 23:26:13 -04:00
LainGitHubDaniel Campora
 		09a7e6f617 [Deepseek v3.2] Remove extra logics in indexer (#26465) 
Signed-off-by: Siyuan Fu <siyuanf@nvidia.com>
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
Signed-off-by: Lain <siyuanf@nvidia.com>
Co-authored-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
 2025-10-21 23:34:03 +00:00
Daniel CámporaandGitHub 80e9452984 [Deepseek v3.2] Optimize top_k_per_row (#26763) 
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
 2025-10-21 08:30:07 +00:00
Isotr0pyandGitHub 3125d79950 [Chore] Remove unused PolyNorm layer (#27110) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-10-17 19:03:43 +00:00
Elvir CrnčevićGitHubmgoinVarun Sundar Rabindranath
 		7b03584de8 Silu v2 (#25074) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: elvircrn <elvircrn@gmail.com>
Signed-off-by: Elvir Crnčević <elvircrn@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Varun Sundar Rabindranath <varunsundar08@gmail.com>
 2025-10-10 15:19:53 +00:00
Barry KangGitHubSimon MoYongye ZhuChen Zhang
 		127c8b782a Add gather_indexer_k_quant_cache kernel (#25931) 
Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
Signed-off-by: Simon Mo <simon.mo@hey.com>
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
 2025-10-08 04:58:57 +00:00
Daniel CámporaGitHubyoukaichao
 		e1098ced95 Add topk logits torch op for DS3.2. (#25945) 
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
Signed-off-by: Daniel Cámpora <961215+dcampora@users.noreply.github.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
 2025-10-07 10:07:32 +00:00
Michael GoinandGitHub 5d5146eee3 [CI/Build] Conditionally register cutlass_fp4_group_mm to fix building on Hopper (#26138) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-10-02 20:32:38 -07:00
+7
Yongye ZhuGitHubChen ZhangyoukaichaoLucas WilkinsonRobert ShawLucas Wilkinsonyewentao256Wentao YemgoinLucia FangLucia FangNickLuccheSiyuan FuMatthew BonanniXiaozhu MengBarry Kang
 		fa7e254a7f [New Model] DeepSeek-V3.2 (Rebased to Main) (#25896) 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
Signed-off-by: Lucia Fang <fanglu@meta.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Lucia Fang <116399278+luccafong@users.noreply.github.com>
Co-authored-by: Lucia Fang <fanglu@meta.com>
Co-authored-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Siyuan Fu <siyuanf@nvidia.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Xiaozhu Meng <mxz297@gmail.com>
Co-authored-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
 2025-09-30 17:14:41 +08:00
Matthew BonanniandGitHub 8f3616f422 Remove old cutlass mla (#23961) 
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2025-09-17 14:31:43 +00:00
Kyle SayersandGitHub a0b26701c9 [Transform] Deterministic Hadacore Transforms (#24106) 
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
 2025-09-15 12:59:31 -06:00
Elvir CrnčevićandGitHub 98229db244 [Kernels][DP/EP] Optimize Silu Kernel for R1 (#24054) 
Signed-off-by: elvircrn <elvircrn@gmail.com>
 2025-09-13 00:17:27 -07:00
Woosuk KwonandGitHub 5febdc8750 [Chore] Remove unused batched RoPE op & kernel (#24789) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-09-13 00:08:20 -07:00
TaehyunKimGitHubWyldeCatJee Jee Li
 		9bd831f501 [Model] New model support for Motif-1-Tiny (#23414) 
Signed-off-by: ca1207 <ca1207zzz@gmail.com>
Signed-off-by: TaehyunKim <73943231+ca1207@users.noreply.github.com>
Co-authored-by: WyldeCat <skan1543@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-09-10 23:29:40 -07:00
Ming YangGitHubyoukaichao
 		86173ad593 [Kernel] Support decode context parallelism on Blackwell with CUTLASS MLA (#24385) 
Signed-off-by: Ming Yang <minos.future@gmail.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
 2025-09-08 09:27:12 +08:00
yzdsGitHubhongchaoyoukaichao
 		ac201a0eaf [Feature] Support Decode Context Parallel (DCP) for MLA (#23734) 
Signed-off-by: hongchao <hongchao@msh.team>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: hongchao <hongchao@msh.team>
Co-authored-by: youkaichao <youkaichao@gmail.com>
 2025-09-06 13:24:05 +08:00