Commit Graph

Select branches

Hide Pull Requests

dsv41-pd

dsv41-pd-visioncp

main

Mono Color

• 307a90f6d3 Stop losing Kimi-K3 tool calls to reasoning, constraint conflicts, and truncation (#34881) 4 people 2026-08-18 12:42:56 -07:00
• 8bb106cee9 Fix NIXL cleaner grouping for hybrid cache keys (#35130) Wei YangandWei Yang 2026-08-19 02:55:51 +08:00
• 526af15845 [Metrics] Discount queued prefill load by recent cache hits when waiting-queue matching is off (#35248) Hanming Lu 2026-08-18 11:27:21 -07:00
• 7dcaf11987 [Fix] Select custom all-reduce v2 by topology capability (#35061) Xingyu Liuandxingyuliu 2026-08-18 10:30:10 -07:00
• 480033def0 Refactor kv cache event mixin into a recorder (#35164) Ke Bao 2026-08-19 01:20:17 +08:00
• 83d7d45330 fix: preserve output logprobs without input logprobs (#34627) jain-ria 2026-08-18 10:07:13 -07:00
• 3f26febaff [diffusion] fix: decouple encoder parallelism from the dit parallel layout (#34713) MickandClaude Opus 5 2026-08-19 00:16:09 +08:00
• 9485c083bb [NPU] Add mxfp4-w4a4 MOE Quantization Support for NPU (#30319) LinyuanLi 2026-08-19 00:06:05 +08:00
• 97dedd1ce9 [PD] Deferred decode-side KV release for aborts mid-transfer (#35049) Shangming CaiandClaude Opus 4.8 2026-08-18 23:56:33 +08:00
• c60952d933 Exclude multimodal-gen NPU jobs from fast-fail cascade (#35238) hhhh1252023 2026-08-18 23:48:48 +08:00
• 499e90a125 [NPU CI] Reorganize test output/log directory structure with workflow context (#33685) pllimax 2026-08-18 23:46:00 +08:00
• 63d783bbe0 [diffusion] optimization: INT8 Linear + pluggable DiT attention backends for MiniMax-H3 on consumer-level GPUs (#34581) WenhaoZhang 2026-08-18 21:44:39 +08:00
• 0065fbfae1 [Scheduler] Cap prefill-delayer queue target by admission capacity (#35191) paulzhang-tm 2026-08-18 09:40:13 -04:00
• 94eef833fe [diffusion] rl: support cosmos3 (#34197) Andy Ye 2026-08-18 05:42:27 -07:00
• ae6945e112 [kernels] Reorganize ops/diffusion by operator domain behind a lazy facade (#35114) Xiaoyu ZhangandClaude Opus 5 2026-08-18 20:37:43 +08:00
• 7605529bdf Add deepseek_v4_flash_w8a8_8p_in32k_out1k_50ms (#35162) HeYaoandHeYao 2026-08-18 19:41:25 +08:00
• f7101b0ae6 [AMD] MiniMax-M3 : Fuse QKV+index proj for block-fp8 (#32099) YC Yen-Ching Tseng 2026-08-18 12:01:01 +02:00
• 24d625698d [AMD] feat(moe): fold padded-topk_ids fill into fused shared-experts append+remap (#31370) karverma-amd 2026-08-18 04:32:57 -05:00
• 70ee6b1714 [Rust Server] Add e2e latency metadata and fix Sarashina import (#35125) Lianmin Zheng 2026-08-18 02:08:07 -07:00
• 880ab72f34 test: extend NVFP4 Marlin tests to SM120 (#34327) vijay-kodamalla 2026-08-18 04:24:00 -04:00
• fc0b95e7ba Profiling Enhancements [2/3]: detailed execution step annotations (#24911) mohbasit 2026-08-18 04:09:07 -04:00
• 667389c50f [diffusion] chore: filter transformer safetensors by index.json to drop duplicate shard variants (#35107) Emil BogomolovandEmil Bogomolov 2026-08-18 01:05:05 -07:00
• 0111b29031 [Perf] Hoist DSv4 draft-extend SWA write locs; unify SWA graph buffer naming (#34890) Liangsheng Yin 2026-08-18 00:13:28 -07:00
• a779a2a2a5 [Chore] Move version tag helper to release scripts (#35196) Lianmin Zheng 2026-08-18 00:11:12 -07:00
• 5b60b7c651 [DSV4] Turn on mhc post pre fusion by default (#35214) Baizhou Zhang 2026-08-18 00:03:37 -07:00
• 772018fe36 [diffusion] Per-section LoRA adapters on fused linear layers (#34933) Andy Ye 2026-08-17 23:40:45 -07:00
• 5eb117f6ca [XPU] Fix decode graph runner is_current_stream_capturing on non-CUDA devices (#35050) ashwini rathi 2026-08-18 11:58:13 +05:30
• 27596abdc0 [AMD] Update amd k3 cookbook for PR#34580 (#35263) Thomas Wang 2026-08-18 14:19:36 +08:00
• 61600c9f39 [Diffusion][Refactor] Refactor and extract complex RoPE implementation to layers/rotary_embedding for MOVA DiT (#31453) Alexandrandronnie_zheng 2026-08-18 09:14:35 +03:00
• e6df23f3c2 refactor: rename chat response token IDs (#35225) Jiajun Li 2026-08-17 23:07:43 -07:00
• 0077f84d37 [mem_cache][8/N] refactor: move MambaPoolHost to pool_host.mamba (#31180) Shuwen Wang 2026-08-18 13:22:45 +08:00
• ea27e3ddab [AMD] Fix Quark Shared Experts Fusion Gate after load-time-override Removal (#35200) Colin Z 2026-08-17 22:10:01 -07:00
• 9401db3f29 [AMD] Scope the EAGLE greedy-verify TP broadcast to ROCm only (#35195) Zhiyao Jiang 2026-08-18 00:38:24 -04:00
• 8ea5229d42 [AMD] Add the Kimi-K3 MI35x perf benchmarks in nightly (#34985) 3 people 2026-08-17 21:23:51 -07:00
• d528192bf9 Skip inkling sheared bias under batch invariance (#35161) Ke Bao 2026-08-18 12:22:58 +08:00
• d01812d89e [AMD] Optimize KIMI-K3 with Triton MLA decode kernel by tuning the stage-1 geometry for gfx950 (#34580) amd-danli103andThomas Wang 2026-08-18 12:16:14 +08:00
• 53621818e4 [Docs] Enable PD disaggregation for DSV4 low-latency recipes (#35224) Baizhou Zhang 2026-08-17 20:07:27 -07:00
• f44a130c5e [DCP] Drop the prefill index-selection syncs by taking each rank's rows by stride (#35084) Khoa PhamandClaude Opus 5 2026-08-17 19:55:51 -07:00
• fcdaaf8a5d [Feature] Optimize TP LMHead with All-to-All (#32313) Siyuan Chen 2026-08-18 10:55:27 +08:00
• d6c837489a [XPU] Enable fused GDN QKV split Triton kernel on XPU (#30144) jiayisunxandMa Mingfei 2026-08-18 10:42:58 +08:00
• 7f51e6bba0 [CPU] Explicitly import sgl_kernel in CPU kernel tests (#35119) Ma Mingfei 2026-08-18 10:20:28 +08:00
• d55f1c28e2 [diffusion] feat: load quantized H3 text encoder checkpoints (#34986) MickandYiqi Yang 2026-08-18 09:10:54 +08:00
• 0ea262e6e5 [XPU] xpu kernel release workflow (#33679) Zaili Wang 2026-08-18 09:07:48 +08:00
• c2c1c4d3eb [CI] Move DSA PD+MTP+CP Layersplit test to basic B300 test suite (#35220) Baizhou Zhang 2026-08-17 17:44:31 -07:00
• 9ffc2856fb docs: sync LMSYS SGLang blog cards (#35218) sglang-botandsglang-bot 2026-08-17 17:30:28 -07:00
• 91144797c5 Update Qwen3.5 H200 FP8 for AgentX HiCache MTP (#35194) Faradawn Yang 2026-08-17 17:12:07 -07:00
• c0b6474b43 [Spec] Reduce host-side overhead in ngram draft prep (#35207) Liangsheng Yin 2026-08-17 16:40:06 -07:00
• b3c8f0d923 config: one control-plane log for the process (#35028) Cheng Wan 2026-08-17 16:19:00 -07:00
• c70c7d72a8 config: the readback and the resolving view say what they are (#35027) Cheng Wan 2026-08-17 16:18:19 -07:00
• cba3c5d5ac config: the per-instance families read the bags (#35026) Cheng Wan 2026-08-17 16:17:53 -07:00
• a97bc8db32 config: the DP/EP topology reads come from the parallel bag (#35025) Cheng Wan 2026-08-17 16:17:26 -07:00
• d2bc697396 spec: size the speculative buffers from the bags, not the startup record (#35024) Cheng Wan 2026-08-17 16:16:56 -07:00
• 3d7ec00179 config: publish before a process reads configuration (#35023) Cheng Wan 2026-08-17 16:16:20 -07:00
• 2b278b4ac4 config: retire the multi-engine accommodation in the runtime context (#35022) Cheng Wan 2026-08-17 16:15:33 -07:00
• bc312d185d Clean deprecated DeepSeek V4 Environs (#34926) Baizhou Zhang 2026-08-17 16:07:00 -07:00
• b42abbb1ba [metrics] Fix prefill FLOPs estimate to count prefix and per-request causal pairs (#34316) Lennox Fu 2026-08-17 15:18:54 -07:00
• b956e916ae docs(cookbook): add Qwen3.8-27B DGX Spark configs (#35121) Jimmy ShongandClaude Opus 5 2026-08-17 15:04:17 -07:00
• 816ea65058 [AMD] Add Kimi-K3 8-GPU MI35x nightly accuracy CI (#32568) 3 people 2026-08-17 14:48:29 -07:00
• 198a7b2fc9 [Misc] Clean up python/sglang package structure (#35062) Lianmin Zheng 2026-08-17 14:24:35 -07:00
• 770e7b47a2 [Spec] Support output logprobs with DSpark (#34478) 3 people 2026-08-17 14:23:24 -07:00
• 032fe9c891 [Spec] Relay ngram accept tokens through the FutureMap (#35198) Liangsheng Yin 2026-08-17 14:21:07 -07:00
• 861eca8e25 docs: add NVFP4 quantization option to Kimi-K3 deploy panel (#35168) Yuhao Yang 2026-08-18 02:01:47 +08:00
• 2e7c85da68 [PD] Preserve decode KV across retraction in HiCache (#34801) cctryandcctry 2026-08-17 08:49:11 -07:00
• af743371cc Clean up environ.py: remove dead env vars, unify deprecation handling, move examples to a unit test (#35060) Lianmin Zheng 2026-08-17 06:53:34 -07:00
• d97b796c16 [diffusion] chore: reuse SRT CLIP encoder blocks (#35004) Mick 2026-08-17 19:51:51 +08:00
• 6e8a4abb57 Add bit-exact class for MTP (#35143) Ke Bao 2026-08-17 19:51:39 +08:00
• e9ad8102a2 [diffusion] chore: reuse SRT SigLIP in Pi0.5 (#34992) Mick 2026-08-17 19:33:36 +08:00
• f33b83b4cc [diffusion] fix: fix h3 swap peft SwiGLU lora_B halves when loading FFN Lora (#34940) WenhaoZhang 2026-08-17 18:47:31 +08:00
• 82995a001b Stabilize GB300 nightly tests (#35044) Mohammad Miadh Angkad 2026-08-17 18:30:16 +08:00
• 744740dbea [XPU] upgrade sglang xpu backend to PyTorch 2.13 (#31751) 3 people 2026-08-17 18:29:15 +08:00
• c82e928fe5 [AMD] diffusion: normalize ModelOpt-FP8 weights to e4m3fnuz on gfx942 (#35111) kangwangamd 2026-08-17 17:35:10 +08:00
• 056808723e [AMD] Guard ROCm 7.0 build from using hipMemcpyBatchAsync (#35128) Alan Kao 2026-08-17 17:22:58 +08:00
• 92bce3d7bb [AMD] [GLM5] fp8 MLA absorbed bmm for GLM-5.2 on gfx950 (#30519) 3 people 2026-08-17 17:15:16 +08:00
• 8cc112d486 [DSA] Skip indexer KV cache for skip-topk layers (#30531) 3 people 2026-08-17 17:02:23 +08:00
• 7c423cfd41 [PD] Avoid unused PREBUILT prompt tensor transfer (#35070) YAMY 2026-08-17 01:48:12 -07:00
• 711bdacb82 [Spec] Resolve shared-read ends from the backend declaration alone (#35059) Liangsheng Yin 2026-08-17 01:35:29 -07:00
• b83d507cd7 [NPU] Support DeepSeek-V4 DSpark and refactor DSV4 cache management (#33676) 6 people 2026-08-17 16:27:44 +08:00
• e03c53fc13 docs(cookbook): Qwen3.8-27B deployment grid rework (#35065) Jimmy ShongandClaude Fable 5 2026-08-17 00:56:08 -07:00
• 4cad864361 Fix sconv track refresh on graph capture (#35042) Ke Bao 2026-08-17 15:51:45 +08:00
• 5769b6d637 [JIT Kernel] Migrate causal_conv1d_fwd and causal_conv1d_update from AOT to JIT (#35031) Mohammad Miadh AngkadandMohammad Angkad 2026-08-17 15:22:37 +08:00
• 0d8c850a35 [Fix] Read the DSA prefill CP flag from the parallel config bag in bootstrap (#35110) Liangsheng Yin 2026-08-17 00:21:41 -07:00
• 721e359ca7 Suppress expected FlashInfer TRT-LLM workspace warnings (#34921) Mohammad Miadh Angkad 2026-08-17 15:16:16 +08:00
• 12a455a910 Fix world-size-one aliasing in MLP batch sync (#34997) Lianmin Zhengandwangwenchen0407 2026-08-17 00:04:09 -07:00
• f7a404e9c3 Fix rope config compatibility and VL/transformers-fallback weight loading (#31575) vikram singh shekhawatandClaude Sonnet 4.5 2026-08-17 12:23:59 +05:30
• 0099107e8b Revert "[AMD] [GLM5] Fuse shared-expert append into aiter grouped-topk (skip per-layer append kernel)" (#35105) Liangsheng Yin 2026-08-16 23:49:49 -07:00
• 43226af812 fix(hicache): limit load-back pending to write-back (#34519) ziang663andZhangheng 2026-08-17 14:23:54 +08:00
• eafbe2cb6f [CI] Install sgl-eval in xeon (CPU) Docker image (#34818) MingxuZh 2026-08-16 23:00:44 -07:00
• 07a28ec5cf docs: fix Qwen3.8-27B mamba ratio calculator for speculative decoding (#35064) Jimmy ShongandClaude Fable 5 2026-08-16 22:54:57 -07:00
• 9be3044b9c [Engine] Freeze GC after server warmup (#34999) Lianmin ZhengandJialin Ouyang 2026-08-16 22:41:36 -07:00
• eb61cb2823 [AMD] Support prefill context parallel two batch overlap for DeepSeek V4 (#33480) Wang, FangYuan 2026-08-17 13:40:29 +08:00
• 4b06f917ca Upd: code owners (#35094) HAI 2026-08-16 22:27:54 -07:00
• f3225bceb3 [DSV4] Emit TMA-aligned UE8M0 scales for FP8 einsum (#34277) Kaixi 2026-08-17 07:06:41 +02:00
• 0fb040cbeb [DCP]Localize HiCache DCP indices once per transfer, not per layer (#34889) Khoa PhamandClaude Opus 5 2026-08-16 21:54:51 -07:00
• 92b1d382c7 [Fix] Correct dense FP8 Marlin bias ordering (#35020) Enrique Shockwave 2026-08-17 04:43:36 +01:00
• b6d7602914 [CPU] Add support for Gemma4 on Xeon (#22498) 4 people 2026-08-17 10:52:26 +08:00
• 3adc70bb5e [MoE] Add H20 fp8_w8a8 tuned configs for Qwen3.8 (triton 3.7.1) + fix Qwen3_5MoeForCausalLM tuning (#34795) TobyMint 2026-08-17 10:41:03 +08:00
• f019f0b064 [Docs] Feature MiniMax-H3 in the popular-models banner (#35068) zijiexiaandClaude Opus 5 2026-08-16 19:09:26 -07:00
• 0e500feae6 fix tpot by adjusting the sliding max-prefill-size window size (#34856) hanwlax 2026-08-17 09:50:48 +08:00
• 8e0499bd50 [AMD] [GLM5] Fuse shared-expert append into aiter grouped-topk (skip per-layer append kernel) (#31323) 3 people 2026-08-17 09:22:26 +08:00
• 0e178c3d22 [diffusion] chore: reuse srt siglip vision model (#34988) Mick 2026-08-17 09:16:17 +08:00