Commit Graph

Select branches

Hide Pull Requests

bot/update-est-time-20260928

dsv41-pd

dsv41-pd-visioncp

main

Mono Color

• ce1736fcc6 [Spec] Remove dead kernel params; fix stale comment in trtllm_mla (#25010) Liangsheng Yin 2026-05-11 14:50:46 -07:00
• 893dfb7b74 Add libertyeagle to CI_PERMISSIONS.json (#25011) Lianmin Zheng 2026-05-11 14:44:07 -07:00
• 42bcbc00d4 [Spec] Drop Rule 5 (_len / _lens ban) from speculative naming rule (#25012) Liangsheng Yin 2026-05-11 14:35:34 -07:00
• d3edfb579b [connector] Add Azure Blob Storage connector (az:// and *.blob.core.windows.net URLs) (#23995) Bruce Changlong Xu 2026-05-11 14:20:22 -07:00
• da0eeb82f2 perf: add --prefill-only-disable-kv-cache to skip KV pool allocation (#23675) Jia Guo 2026-05-11 13:10:24 -07:00
• c7e53e68a2 [Spec] Fix ngram metric off-by-1 in num_accepted_drafts_per_req_cpu (#24965) Liangsheng Yin 2026-05-11 12:25:18 -07:00
• 7407a62c1c [Docs] Update MiniCPM-V-4.6 documentation and deployment configuration (#24991) Yihao Wang 2026-05-11 11:10:19 -07:00
• 4b6f776889 feat(kv-events): publish SWA radix cache events (#24718) Yan Ru Pei 2026-05-11 10:31:45 -07:00
• 95985f983d feat(trace): support SGLANG_TRACE_LEVEL env var for startup trace level (#24716) TianheandClaude Sonnet 4.6 2026-05-11 10:31:03 -07:00
• 2e69266f84 [AMD] avoid aiter re-installing triton in amd_install_dependency (#24981) Bingxu ChenandCursor Agent 2026-05-11 23:05:16 +08:00
• aeb8fefc25 [AMD] Pin cache-dit==1.3.0 in rocm.Dockerfile + AMD CI install script (#24924) Bingxu ChenandCursor Agent 2026-05-11 22:32:13 +08:00
• d9cb38012e Update MiMo V2.5 cookbook image to nightly (#24983) Ke Bao 2026-05-11 22:04:31 +08:00
• 62edbc37c4 [Doc] Add rerun-test slash command usage (#24979) Ke Bao 2026-05-11 21:30:01 +08:00
• 9c03171f6c Fix gb envs in deployment guide (#24977) Ke Bao 2026-05-11 21:06:02 +08:00
• 36ba60ad49 Register SWA unit tests under unit/mem_cache (#24974) Ke Bao 2026-05-11 20:21:05 +08:00
• 6b6963f426 [AMD] Update scripts/ci/amd/ensure_vram_clear.sh (#24586) YC Yen-Ching Tseng 2026-05-11 18:47:09 +08:00
• 6d30b571b2 [diffusion] fix: fix single-step flow-match timesteps (#24708) Mick 2026-05-11 18:09:24 +08:00
• c027ae677c ci: align torch CUDA wheel checks (#24940) Hank Han 2026-05-11 16:22:20 +08:00
• f7ba136279 [NPU] bump sgl-kernel-npu version to 2026.05.01 (#24951) monkeyLoveding 2026-05-11 16:13:39 +08:00
• df441b8fea [NPU] Support shared expert dual stream optimization (#23827) iridiumineandiridiumine 2026-05-11 15:50:15 +08:00
• 1df9edcd01 Use Torch torch.mm for Deepseek V3.2 Indexer GEMM (#23856) Brayden Zhongandb8zhong 2026-05-11 03:41:05 -04:00
• 1d80a1a9fe Use Cute-DSL NVFP4 quantization kernels (#23745) Brayden Zhongandb8zhong 2026-05-11 03:40:02 -04:00
• ea217a2bf0 ci: remove Execute Notebooks workflow (#24460) Baizhou Zhang 2026-05-11 00:26:32 -07:00
• 044bb88a97 fix: SGLANG_RADIX_FORCE_MISS chunk-cache passthrough (#24950) Cheng WanandClaude Opus 4.7 2026-05-11 00:07:46 -07:00
• d102b0cbc3 Add CODEOWNERS for EPD module (#24942) Shangming Cai 2026-05-11 14:42:48 +08:00
• 3ffb37789a [AMD] Fix DeepSeek import cascade by supporting both pre- and post-#2958 aiter fused_qk_rmsnorm APIs (#24799) Bingxu Chenandbingxche 2026-05-11 14:41:57 +08:00
• faad02b3dd spec: centralize EagleDraft{,Extend}Input.hidden_states shape (#24926) Liangsheng Yin 2026-05-10 22:49:20 -07:00
• 6e5b4de01a [diffusion] fix: further align ltx2.3 accuracy with tp (#24660) Mick 2026-05-11 13:42:08 +08:00
• ed70226ec1 [Diffusion][NPU][GPU] Fix SANA model execution error (#24798) Thomas 2026-05-11 13:41:36 +08:00
• 9ec2880eca [NPU] [Bugfix] Wan quantization fix (#24540) Артем Савкинandronnie_zheng 2026-05-11 08:32:57 +03:00
• 5207f074a4 Breakable Cuda Graph Support for bs > 1 (#24662) Yuwei AnandClaude Opus 4.7 2026-05-10 22:28:49 -07:00
• a623ee4cb5 📝 docs(diffusion): add MXFP8 quantization docs for Wan2.2 on Ascend NPU (#24918) Junlin Wu 2026-05-11 13:13:34 +08:00
• d5e707f132 Fix sgl-kernel-mla-test path after test was moved to test/manual (#24914) 3 people 2026-05-11 13:00:08 +08:00
• 8e2142c15a [MoE] Fix NaN in flashinfer TRT-LLM A2A dispatch by sanitizing padding slots (#24850) Ming Yang 2026-05-10 21:57:43 -07:00
• a6f359d103 [Rerank] Use heapq.nlargest for top_n to avoid full sort (#24871) Tejas Dharamsi 2026-05-10 21:48:37 -07:00
• 22543b1982 [AMD] DSv4 nightly hotfix + schedule-aware --continue-on-error in AMD CI (#24825) Bingxu ChenandCursor Agent 2026-05-11 12:46:32 +08:00
• 9f066cb55b [Docs] Add MiniCPM-V 4.6 cookbook (#24876) Yihao Wang 2026-05-10 21:32:15 -07:00
• 36c93fc6fb [NPU] [Diffusion] Use fused operator to improve Wan model E2E performance. (#24028) 6 people 2026-05-11 12:17:31 +08:00
• 958f35d1e0 ci: run H20 stage with CUDA 13 (#24916) Hank Han 2026-05-11 11:18:41 +08:00
• 126a36a986 [AMD] VRAM cleanup step to AMD nightly test workflows (#24612) YC Yen-Ching Tseng 2026-05-11 11:08:51 +08:00
• b35d14b64d [AMD] Retry logic for lmms-eval installation (#24615) YC Yen-Ching Tseng 2026-05-11 10:55:24 +08:00
• 09a4828db9 [NPU] Fix warmup error with --disable-cuda-graph and mtp (#23819) iridiumineandiridiumine 2026-05-11 09:53:34 +08:00
• 4435a23a51 [NPU]adapt multibatch fia ops (#20177) McZyWu 2026-05-11 09:44:14 +08:00
• 407665a7d4 [NPU] Fix mrope_position computation in Eagle Worker v2 with PlanStream (#23423) silencejade 2026-05-11 09:43:37 +08:00
• 0fc9598b3e [NPU] Support radix-cache with mamba-extra-buffer for Qwen3.5 (#23891) silencejade 2026-05-11 09:40:44 +08:00
• e9a15b95da [Fix] Disable FlashInfer allreduce fusion under deterministic inference (#24629) Jimmy Shong 2026-05-10 20:04:52 -05:00
• aa7a9af12f fix: STANDALONE spec-decode hidden-size mismatch crash (#24217) 7 people 2026-05-11 08:48:00 +08:00
• 8acb0270fd Followup fix for Custom AR V2 in non NVL scenarios (#24742) Brayden Zhongandb8zhong 2026-05-10 19:57:46 -04:00
• b202778aa5 Fix reduce_scatterv producer contract for SUM_LEN (#24785) YAMY 2026-05-10 16:51:13 -07:00
• 2473659e76 [NPU]Documentation update for communications quantization feature (#24668) egvenediktov 2026-05-10 23:49:21 +03:00
• d82e339ce2 [Session R3] Add routed_experts_start_len for absolute routing slice control (#24851) 5 people 2026-05-10 10:04:43 -07:00
• 9150e77399 [Model] Add MiniCPM-V 4.6 support (#24855) Yihao Wang 2026-05-10 12:24:17 -04:00
• 335dbd60b4 Support Intern-S2-Preview (#24875) RunningLeon 2026-05-10 22:17:30 +08:00
• 59faf986b2 [PD] Unify dsv4 dispatch with swa (#24888) Ke Bao 2026-05-10 22:01:13 +08:00
• 2f06867128 Optimize MHC pipeline: DeepGemm, fused norm, fused hc_head (#24775) 3 people 2026-05-10 19:03:37 +08:00
• bd0aa22309 Fix PD bootstrap failure handling (#24772) Yuhao YangandCheng Wan 2026-05-10 19:02:47 +08:00
• 8cc16c9974 [Spec] Cleanup idle stub and shape-check patterns (#24881) Liangsheng Yin 2026-05-10 02:39:53 -07:00
• c7f674e427 [Bug] Add dsv4 state_type branch to mooncake disaggregation (#24878) 3 people 2026-05-10 01:13:46 -07:00
• d08744238a [Spec V1] Split draft-extend phase from EagleDraftInput into new EagleDraftExtendInput (#24859) Liangsheng Yin 2026-05-10 01:07:45 -07:00
• d3fd91ed97 [Gemma4] Optimize Gemm4 with fused Q/K/V RMSNorm + per-expert FP8 ckpt loader (#24696) Yuan Luoandluoyuan.luo 2026-05-10 15:24:12 +08:00
• a87fb399de [spec decoding] support kimi-k2.5-eagle3-mla (#24826) Qiaolin Yu 2026-05-09 23:57:39 -07:00
• b4d347e86e [SPEC V2] fix: skip stale state updates in spec-v2 overlap (#23456) shuwenn 2026-05-10 14:56:24 +08:00
• cfd3fd00d0 [RL] Call torch.cuda.empty_cache() for in-place pause mode to avoid OOM (#24854) 3 people 2026-05-09 23:36:52 -07:00
• 44efc23a9a [diffusion] CI: add cache-dit CI tests (#19213) Chi McIsaac 2026-05-10 01:38:41 -04:00
• 1e6c6d1f07 [Utils] Make request dump robust to unpicklable server_args and large meta_info (#24767) 3 people 2026-05-09 21:41:41 -07:00
• 9578ba1b57 [Utils] Refactor device cache emptying (#24861) Stefan HeandBiao He 2026-05-09 21:28:00 -07:00
• 47483001b6 [PrefillDelayer] support NCCL all-gather for cross-DP info sync (#24768) 3 people 2026-05-09 21:20:03 -07:00
• 7edb4c3cea [NUMA+Ray] Fix NUMA NVML handle resolution under shuffled CUDA_VISIBLE_DEVICES (#24766) 3 people 2026-05-09 21:18:39 -07:00
• f9c315e85d docs: clarify how /tag-and-rerun-ci kicks off CI on the current commit (#24774) 3 people 2026-05-09 20:28:41 -07:00
• c95454b341 speculative: drop dead params/returns/no-ops (#24865) Liangsheng Yin 2026-05-09 15:53:31 -07:00
• b735ca178c Update CODEOWNERS for /sgl-kernel/csrc/musa (#24746) R0CKSTAR 2026-05-10 05:45:13 +08:00
• 12f42f2e7e Support Gemma3/4 + Eagle3 (#23976) Charles Chen 2026-05-09 13:34:56 -07:00
• 8087e07d52 [UnifiedRadixTree]: Align cache_empty_result with RadixTree (#24779) luchangliandZhangheng 2026-05-09 23:52:22 +08:00
• ef5e9f8aba [DSV4] Cherry pick missing commits from deepseek_v4 branch and enhance tests (#24793) 3 people 2026-05-09 04:15:37 -07:00
• 4b23f6bdc5 Fix performance regression on Deepseek V3 on moe-runner-backend=triton on SM90 (#24562) Brayden Zhongandb8zhong 2026-05-09 06:49:12 -04:00
• 05d1ab51e8 Enable PDL for various kernels in DSV32/GLM5 (#23965) Brayden Zhongandb8zhong 2026-05-09 06:42:56 -04:00
• d5564c2a96 fix(fa3): translate page table to SWA loc in EAGLE3 topk>1 spec metadata (#24617) shuwenn 2026-05-09 18:22:45 +08:00
• a309f1f8f4 fix(cuda_graph): zero out_cache_loc_swa on pad and use int32 (hybrid-SWA accuracy fix) (#24743) JoyFuture 2026-05-09 18:22:12 +08:00
• ba625d5290 slash command rerun UX: emoji semantics + result writeback (#24802) Liangsheng Yin 2026-05-09 03:19:24 -07:00
• f4b7e73699 Enable trtllm-gen BF16 MoE for MTP (#24260) Brayden Zhongandb8zhong 2026-05-09 06:14:17 -04:00
• f1a9a455e0 Revert "[NPU] fix profiler on npu" (#24815) sglang-npu-bot 2026-05-09 17:53:02 +08:00
• e2527df8b6 [NPU] fix profiler on npu (#24685) zhaozx-cn 2026-05-09 17:48:24 +08:00
• fd636410a2 Restrict fa_skip_kv_cache to non-MLA backends (#24097) Jia Guo 2026-05-09 02:25:02 -07:00
• 8f33bee31b Reland Cute-DSL FP4 dense GEMM (#23590) Brayden Zhongandb8zhong 2026-05-09 05:20:58 -04:00
• d49fc092cb [Bug Fix] GLM-5.1: drop constexpr on page_indice_batch_offset, skip offloader post_init on draft worker, support N=32 in copy_to_gpu_no_ce (#23550) Yuxuan Zhang 2026-05-09 09:43:45 +02:00
• 9d12f9e6fa [HiCache] ci: lower est_time for test_hicache_spec_file_storage (#24713) shuwennandClaude Opus 4.7 2026-05-09 15:33:18 +08:00
• 78da0d3106 [Spec] Move accept_tokens off EagleDraftInput; pass via method arg (#24735) Liangsheng Yin 2026-05-08 23:24:18 -07:00
• 1610aa77ab Reduce gemma4 moe deterministic test runtime (#24754) Khoa Pham 2026-05-08 20:46:56 -07:00
• 8e534e8f15 [diffusion] fix: fix diffusers executor crash when component residency manager is absent (#24573) Chi McIsaac 2026-05-08 23:45:06 -04:00
• 44a527f6f4 fix patch_torch test queue race (#24739) Liangsheng Yin 2026-05-08 20:25:59 -07:00
• 590b13b513 [diffusion] fix: fix NCCL deadlock in ulysses sp when sequence length has remainder (#24694) storyicon 2026-05-09 11:05:37 +08:00
• 50ed01674e fix is_arch_support_pdl function usage (#24600) Polisetty V R K Jyothendra VarmaandMa Mingfei 2026-05-09 07:09:34 +05:30
• 1613bae412 [Spec] Disambiguate verified_id into bonus_token(s) / accept_tokens (#24724) Liangsheng Yin 2026-05-08 18:24:33 -07:00
• a61a14f416 [KDA] Optimize prefill kernels with diagonal and recompute fuse (#24271) Yuan Luoandluoyuan.luo 2026-05-09 08:52:51 +08:00
• 9ee830346f Disable Custom AR V2 when in multi-node (#24729) Brayden Zhongandb8zhong 2026-05-08 20:50:05 -04:00
• d1c5937428 env: add SGLANG_RADIX_FORCE_MISS to force radix prefix-cache miss (#24726) 3 people 2026-05-08 17:46:38 -07:00
• 560829a171 feat(scheduler): add adaptive queue-based prefill delayer trigger (#23189) YAMY 2026-05-08 16:54:30 -07:00
• 6971a03fe6 fix(fa3): skip scheduler_metadata precompute under DP attention (#24632) YAMY 2026-05-08 16:19:20 -07:00
• 62c2e091f6 [PD] MORI-IO: Add state transfer, inline transfer model, and high-concurrency fixes (#22665) Niko Ma 2026-05-09 07:07:22 +08:00
• 190b15c8fe [AMD] Register 8 CPU-bound unit tests for AMD 1-GPU PR CI (#24569) Michael 2026-05-09 07:01:58 +08:00