Commit Graph

Select branches

Hide Pull Requests

dsv41-pd

main

Mono Color

• 292e3ccc0c [ci][xpu] Re-seed the wan2_1_t2v_1.3b perf baseline on Arc Pro B60 (#39955) ashwini rathi 2026-09-21 10:34:35 +05:30
• c74a4037fb mooncake: probe pointers via cuda.bindings instead of ctypes libcudart minke.yu 2026-09-21 12:46:25 +08:00
• b963295489 mooncake: support host-memory payloads with intra-node NVLink transport minke.yu 2026-09-21 11:53:26 +08:00
• 1da8ac10e1 Update to the cookbook for XPU-supported models (#33649) ZiruandNiu Ziru 2026-09-21 11:26:09 +08:00
• 62ba964848 Fix: post-load staging regression breaks offload meta/sharded_gpu modes (#38779) jianzhao-xu 2026-09-21 11:19:07 +08:00
• ab03a8e7eb [Perf] Fork-safe import: no CUDA context at import time, lighter argument parsing (#40201) Xueshen Liu 2026-09-20 22:48:35 -04:00
• 176dbcb85d [npu]add chunk gdn kernel and unify ssm state layout for ascend gdn backend (#36187) zhaozx-cn 2026-09-21 09:51:19 +08:00
• 6ad78f2281 [diffusion] docs: add verified DGX Spark recipe for Qwen-Image 2.1 (#40487) MickandMick Qian 2026-09-21 08:49:35 +08:00
• b912db67ea [diffusion] fix: keep Qwen-Image 2.1 prefix KV per layer under Cache-DiT (#40472) WenhaoZhang 2026-09-21 08:48:31 +08:00
• 501b7851e4 [diffusion] CI: guard E2E/loading latency with runner-aware baselines (#39206) MickandMick Qian 2026-09-21 08:43:22 +08:00
• 3a0324fb9b [diffusion] optimization: reduce Qwen-Image 2.1 vae and graph warmup memory (#40481) MickandMick Qian 2026-09-21 08:42:02 +08:00
• 76a9065bef [Fix] Raise on undelivered embeddings in send_with_url, fix broken tests (#40502) Liangsheng Yin 2026-09-20 17:35:27 -07:00
• 4027740569 [sgl-router] refactor - session-aware policy (#40379) Kan WuandClaude Fable 5.1 2026-09-20 17:22:36 -07:00
• aedda8377e [sgl-router] refactor - layout BucketResolver, Bucket, EngineGroup and implement PowerOfTwo (#40241) Kan WuandClaude Fable 5.1 2026-09-20 16:57:07 -07:00
• 4a9dc5c4af [sgl-router] refactor - move policy-required states under src/state (#40272) Kan WuandClaude Fable 5.1 2026-09-20 16:49:23 -07:00
• acd20a516e [CI] Give the kernel lane a 5090 suite and move kernel-only tests off the general lane (#40496) Liangsheng Yin 2026-09-20 16:46:53 -07:00
• 42875bcd2a fix(modelopt): dispatch NVFP4 MoE on the cached backend, not the live global (#38932) 3 people 2026-09-20 16:28:54 -07:00
• 2fa6b94e34 [Perf] Fuse the glm5_next mHC attn->MLP boundary (#39200) Mohammad Miadh Angkadandmmangkad 2026-09-20 23:20:37 +00:00
• 983e643854 [Feature] support bf16 MoE router and mxfp4 MoE for MiMo V2 (#40448) ollybbmonster 2026-09-21 07:13:59 +08:00
• 2e2d8a2fda [CI] Drive per-commit stage jobs from a runner table instead of copied job blocks (#40495) Liangsheng Yin 2026-09-20 15:43:46 -07:00
• d97aed2c90 Fix TopK v2 fallback when 16-block cluster capacity is zero (#40163) luoroger37andHank Han 2026-09-21 06:41:41 +08:00
• f31a7bd45c Use pinned memory for asynchronous sampling metadata transfers (#39777) 3 people 2026-09-21 06:31:31 +08:00
• 95521da18d [DeepSeek-V4.1] Bound dense prefill indexer memory (#40217) Harmya Bhatt 2026-09-20 16:43:19 -05:00
• c2c3629f2d [Kimi-K3] O(1) expert weight lookup in load_weights (#38805) 4 people 2026-09-21 05:39:45 +08:00
• f6483e479f [Test] Drop cause-less disabled tests, fix XPU lane, demote quality gates off base-c (#40288) Liangsheng Yin 2026-09-20 14:36:02 -07:00
• d229952e25 [Fix] Preserve model runner contracts in prefill CUDA graphs (#35452) 3 people 2026-09-20 13:53:14 -07:00
• 745de73ba3 Add CODEOWNERS entry for sglang-renderer (#40483) Shangming Cai 2026-09-21 01:37:50 +08:00
• b3e4d198af [PD] Bound cached-prefix DCP transfers by pack capacity (#40376) Khoa Pham 2026-09-20 10:17:15 -07:00
• 80da4432d0 [Simulator] Fix meta host memory budgets on constrained runners (#40440) Shuwen Wang 2026-09-21 00:42:55 +08:00
• 3dbdd700e2 [CI] update CI permissions (#40474) WenhaoZhang 2026-09-21 00:07:37 +08:00
• e97614d10c [Qwen4-Exp] Build the offloaded PLE table on the meta device so --ple-offload-embedding never materialises it on the accelerator (#39928) Jimmy ShongandYangmin Li 2026-09-20 08:28:25 -07:00
• 5f017ffabb Update test cases and performance testing framework (#40392) ZY Y 2026-09-20 22:42:00 +08:00
• 404dee10c0 [NPU] add coverage-based precision test selection pipeline (#38339) chenyang08056032 2026-09-20 22:40:55 +08:00
• 8923f4d779 [Test] Fix optimistic prefill disaggregation test after mamba radix cache removal (#40469) Mohammad Miadh AngkadandMohammad Angkad 2026-09-20 14:39:34 +00:00
• fa826e08b1 Reuse shared compressed KV dequantization in DeepSeek V4.1 CP prefill abing 2026-09-19 10:24:01 -07:00
• 3810f531a8 Support V4.1 decode vision MegaMoE SYChen123 2026-09-18 19:13:10 +08:00
• 2580c24d1b Support V4.1 DP attention in DP-only DSpark PD SYChen123 2026-09-18 19:11:24 +08:00
• 791c7850d0 [Diffusion] Enable shared RMSNorm dispatch for SenseNova-U1 (#39705) faceless voidandronnie_zheng 2026-09-20 22:08:02 +08:00
• 4f22146e51 Avoid host synchronization in DeepSeek V4.1 CP prefill abing 2026-09-18 02:28:12 -07:00
• 12e3b82e52 run pass cp+megamoe+bcg abing 2026-09-17 04:04:38 -07:00
• 8305f66fc8 fix bug abing 2026-09-19 02:32:27 -07:00
• 21a4a16b4b update code abing 2026-09-17 19:43:41 -07:00
• fc954b7e08 add test abing 2026-09-16 00:26:02 -07:00
• c2059c4fb2 run pass llm cp abing 2026-09-15 23:41:20 -07:00
• 7b1c2ed0a4 [rust-renderer] Standalone preprocessing (#36718) 4 people 2026-09-20 17:03:12 +03:00
• 6880a47955 [diffusion] docs: simplify Qwen-Image 2.1 cookbook (#40455) MickandMick Qian 2026-09-20 20:39:26 +08:00
• c610c40399 [sgl-router] refactor - config and organize CLI options (#39867) Kan Wu 2026-09-20 04:40:04 -07:00
• efa7be2091 [Simulator][Compatibility] Adapt to latest KV cache pool interfaces (#40418) Ruiyan Ma 2026-09-20 18:00:06 +08:00
• 0024efa0de [CI] Derive registered-test kind from the registry call instead of the path (#40294) Liangsheng Yin 2026-09-20 02:01:22 -07:00
• 671630abf1 [sgl-router] refactor - main startup logic (#39861) Kan WuandCursor 2026-09-20 01:55:34 -07:00
• 2a0cb2f04e [Diffusion][MiniMax-H3] Add SM120 Sage compute for SubBlock sparse attention (#40116) HuangJi 2026-09-20 16:40:28 +08:00
• 414adef060 [CI] skip srt rust extension builds for diffusion-only PRs (#40293) MickandMick Qian 2026-09-20 16:33:23 +08:00
• dc002c85fc [Test] Fix OOT DFlash hook test resolving the draft config over the network (#40427) Liangsheng Yin 2026-09-20 01:25:34 -07:00
• 9f3d275940 [HiCache] Fix sparse hybrid transfer layer IDs (#37870) Shuwen WangandSeokhoon Kang 2026-09-20 16:24:24 +08:00
• e54009240a [AMD][DSV4] feat: enable DSpark with fp8 unified_kv on gfx950 (#38901) amd-danli103andHAI 2026-09-20 16:16:39 +08:00
• a8a4d86be9 Remove swa and mamba radix cache (#40313) Ke Bao 2026-09-20 16:16:27 +08:00
• 5c69e32abe [NPU] [DOC] fix typos, heading levels and terminology in NPU docs (#40402) amote-i 2026-09-20 15:15:58 +08:00
• f4c256354c [kimi k3][pd disagg] support pp prefill + dcp decode with dspark (#40045) Qiaolin Yu 2026-09-20 00:15:28 -07:00
• 22f02cc339 [Test] Fix scheduler fixtures after prefill burst counting (#40411) Mohammad Miadh AngkadandMohammad Angkad 2026-09-20 07:08:04 +00:00
• 99a44c88d4 Add out-of-tree DFlash extension points (#38740) 3 people 2026-09-19 23:54:46 -07:00
• 9f21fbc34b [GLM-5.3-Flash] Reduce KPool planning synchronization and overlap indexer preparation (#39695) Yuxuan ZhangandXinyuan Tong 2026-09-20 14:51:17 +08:00
• c8eb54c41d Fuse GLM-5.3-Flash KDA projections and prefill metadata (#39688) Yuxuan ZhangandXinyuan Tong 2026-09-20 14:46:33 +08:00
• c1a1eb5f66 docs: sync LMSYS SGLang blog cards (#40276) sglang-botandsglang-bot 2026-09-19 23:35:20 -07:00
• 2d216a11f8 [Model] Serve DeepSeek-OCR-2 with its official 768px local-crop geometry (#38996) chaijiacheng888 2026-09-20 14:17:21 +08:00
• 031bff5dd3 [diffusion] chore: batch qwen-image 2.1 targets and document measured deployment recipes (#40408) MickandMick Qian 2026-09-20 13:59:36 +08:00
• 99d53fe0c2 [sgl-router] refactor - chat_completions() into modules (#39848) Kan Wu 2026-09-19 22:51:25 -07:00
• dd83b54611 Update linear attention code owner directory (#40389) Yuan Luoandluoyuan.luo 2026-09-19 21:13:47 -07:00
• 59dd2fc734 [2/N] [Kernel] Fuse padding-preserving HiSparse slot translation (#39837) Sasha Sidorov 2026-09-19 21:04:03 -07:00
• df0dc44931 [Fix] Forward SWA prealloc reclaim through the DSV4 HiSparse allocator (#40354) Mohammad Miadh AngkadandMohammad Angkad 2026-09-20 03:27:51 +00:00
• 020703923d [PP + HiCache] Add PP Prefetch Tickets for eager cross-stage storage prefetch (#36700) huangtingweiandChao Shi 2026-09-20 11:19:31 +08:00
• 113f6f080e [PD] Enter the custom mem pool once when allocating DCP pack buffers (#40284) 3 people 2026-09-19 19:34:58 -07:00
• d82d653f96 Enable optimistic prefill for Mamba radix-cache models (#40184) Tri Dao 2026-09-19 22:28:11 -04:00
• e9300f643e [Unified Cache][9/N] add opt-in MLA load deduplication for Mooncake Linker (#39565) huangtingweiandZhangheng 2026-09-20 09:56:56 +08:00
• d903351a66 [NPU][bugfix] update low latency quantization input and update MXFP8 tests (#38831) AndyLi429andAndyLi429 2026-09-20 09:55:30 +08:00
• f9c2791460 [diffusion] model: support qwen-image-2.1 (#39983) 3 people 2026-09-20 09:46:09 +08:00
• ee5fcdf0d9 Update SGLANG_KERNEL_NPU_TAG to version 2026.9.0.post5 (#40157) 黄孝君 2026-09-20 09:30:25 +08:00
• d2f291c934 [NPU][DSV4]dsv4 enable cpp (#39820) BourneSun0527andEven Zhou 2026-09-20 09:17:27 +08:00
• 9cc7da2ab0 [MegaMoE] Wire Qwen MoE blocks to DeepGEMM MegaMoE (MXFP4 and NVFP4 experts) (#38080) YAMY 2026-09-19 16:00:38 -07:00
• 3a64faa1f2 Fix disagg PP MTP for GLM-5.2 (#39378) 4 people 2026-09-20 04:55:07 +08:00
• 8139a1740e [Scheduler] Count complete prefill bursts and their tokens (#40006) 5 people 2026-09-19 12:56:15 -07:00
• 7a6c652c77 [HiCache] Auto-size the host pool to fit available host memory (#40135) Zhiqiang Xie 2026-09-19 12:50:43 -07:00
• 2305242f51 [AMD][DSV4] fix: skip compressed-KV metadata on the draft worker in the HIP radix backend (#40205) amd-danli103 2026-09-20 03:13:49 +08:00
• 9e5a62a767 [Logprob] Serve input-logprob temporaries from CUDA-graph-pool dead space (#40038) metamergebotandcctry 2026-09-19 12:03:52 -07:00
• c5326d28a3 [AMD] dsv4: pick kv_splits per index stream, not by occupancy alone (#39968) kkandwunhuang 2026-09-20 02:53:54 +08:00
• 7b67a96640 [DSV4] Chunk the indexer MQA logits by query rows under a free-memory budget (#39095) 3 people 2026-09-20 02:53:20 +08:00
• 993d1fccba [ROCm] Widen the HiCache JIT copy rounds and enable the K-only host pool (#37152) 3 people 2026-09-19 08:58:10 -07:00
• 76f9213a41 [Fix] Keep mHC context out of non-V4 compiled MoE forwards (#40353) Xiaoyu Zhang 2026-09-19 21:41:51 +08:00
• 9e2298e913 [CI] Propagate full-run fast-fail policy to reusable workflows (#40349) Xiaoyu Zhang 2026-09-19 21:07:06 +08:00
• 83e29d6c5a [perf] Optimize w4a8 MoE for glm5.2 on H200 (#38220) Benjamin TruongandXiaoyu Zhang 2026-09-19 19:34:25 +07:00
• 7fac84b639 [DSV4.1] Reduce mHC, metadata and small-batch router overhead (#39704) Xiaoyu Zhang 2026-09-19 19:51:21 +08:00
• d1acbe0746 [DSV4.1] Big fused wo_a quant (#39957) DarkSharpnessandBBuf 2026-09-19 19:46:53 +08:00
• cb22f2451e [Cleanup] Deduplicate kernel tests, diffusion fixtures and benchmark helpers (#40265) Xiaoyu Zhang 2026-09-19 19:45:38 +08:00
• 0b0d2c257a [Fix] Repair CI fixtures and ROCm speculative tree device checks (#40325) Xiaoyu Zhang 2026-09-19 18:16:05 +08:00
• 567d5925fe Fix mxfp4 padding test stubbing an accessor the module no longer imports (#40308) Cheng Wan 2026-09-19 00:43:56 -07:00
• 3a5f52e144 Record a process's placement at publish, not at group build (#40071) Cheng Wan 2026-09-18 23:52:37 -07:00
• 36aa8479ef [Test] Fix fusion-group mocks after runtime context migration (#40290) Xiaoyu Zhang 2026-09-19 14:45:16 +08:00
• 5d703de9e4 [HiCache] Size MHA host pools from device row width (#40304) Lianmin Zheng 2026-09-18 23:37:58 -07:00
• 6533223502 [Lint] Fix logits processor formatting on main (#40303) Xiaoyu Zhang 2026-09-19 14:31:56 +08:00
• 111aeedd37 [Runtime] Add decode CUDA graph hooks for eager logits processing (#40222) Xiaozhu Mengandmxz 2026-09-18 23:27:03 -07:00
• 6e1338dd1e Fix prefetch attempt cleanup on abort (#40262) 3 people 2026-09-18 22:46:17 -07:00