Commit Graph

Select branches

Hide Pull Requests

dsv41-pd

dsv41-pd-visioncp

main

Mono Color

• f6cbdc1dd1 docs(diffusion): refresh skills for latest runtime (#34143) Xiaoyu Zhang 2026-08-09 10:30:46 +08:00
• 38c007dfe5 [diffusion] FLUX.1: route the adaLN LN+modulate sites through the bit-exact fused LayerNorm+modulate kernel (H200 1024^2 lossless denoise -1.2%, e2e wall -2.9%) (#34126) Xiaoyu Zhang 2026-08-09 09:52:37 +08:00
• 6424fec326 [diffusion] Bit-exact data-movement elimination for the Wan causal VAE decoder (H200 LongLive2 704x1280x61f: decode 2.80->2.32 s lossless / 2.12->1.67 s quality=high, e2e -10.7%) (#34125) Xiaoyu ZhangandClaude Fable 5 2026-08-09 09:50:56 +08:00
• 33ed5d4413 [diffusion] perf_logger: SYNC_STAGE_PROFILING must drain the GPU queue for stage records too (fixes 2-3x inflated DecodingStage readings) (#34124) Xiaoyu ZhangandClaude Fable 5 2026-08-09 09:49:52 +08:00
• cea16bf229 Fix Qwen3-MoE producing garbage with the mori a2a backend (#34006) Yuankai Chen 2026-08-09 06:44:01 +08:00
• ba7abd4f92 [AMD] Support DeepSeek V4 DSpark on AMD HIP platform (#30964) Wang, FangYuan 2026-08-09 06:22:14 +08:00
• a59bb931c6 Fix DCP KV head mapping for GQA models (#32858) 3 people 2026-08-08 14:25:09 -07:00
• c2d90db1e3 [CI] Add Kimi-K3 low-latency performance check (#34089) Mohammad Miadh Angkad 2026-08-09 04:42:59 +08:00
• c4f018ba1d [Refactor] Separate ROCm-specific DeepSeek MHA and MLA forward paths (#31531) Diya Peng 2026-08-08 15:39:36 -05:00
• 3fbb5330c7 Fix the router GEMM inaccuracy when using _front_w in Kimi-K3 (#33764) Brayden Zhong 2026-08-08 12:23:40 -07:00
• dc9624deb2 [diffusion] Clean up kernels and shared fast paths (#34085) Xiaoyu Zhang 2026-08-09 00:37:00 +08:00
• ec5199b906 [jit_kernel] Fix missing JIT kernel namespaces (#34106) Mohammad Miadh AngkadandBBuf 2026-08-08 22:15:05 +08:00
• f3ed82b3a8 [inkling] Let Anthropic thinking=disabled map to reasoning effort "none" (#33913) Eric ZhangandClaude Opus 5 2026-08-08 09:59:32 -04:00
• 548ff545c5 [diffusion] fix: guard sage attention sm90 bindings (#34107) 3 people 2026-08-08 16:32:40 +03:00
• db75dfe10f fix: always capture default prefill CUDA graph (#33352) Mick 2026-08-08 19:24:49 +08:00
• cf2d4fd679 docs: clarify K3 VLM feature transport (#34099) Mick 2026-08-08 19:23:00 +08:00
• cfb354bcfc [Bugfix] Fix batched KV free aliasing (#34067) Leon Gao 2026-08-08 03:34:44 -07:00
• a1ca76b24b [Scheduler] Unify WAR read-done gating behind shared-read boundary declarations (#34052) Liangsheng Yin 2026-08-08 03:26:36 -07:00
• 2c0188cc78 [Fix] Give the piecewise CUDA graph test stub an hf_config (#34100) Liangsheng Yin 2026-08-08 02:04:16 -07:00
• f6a6f5bf1e [CI] Trim redundant nightly test registrations (#34070) Liangsheng YinandBaizhou Zhang 2026-08-08 01:42:46 -07:00
• dd5d82bead [NPU] Improve the execution efficiency and maintainability of pr‑test‑npu (#33724) 3 people 2026-08-08 16:42:44 +08:00
• e732c0a9dc [UT][NPU] add unit tests for ascend_torch_native_backend and mla_preprocess (#32505) xdtbynd 2026-08-08 16:15:12 +08:00
• 4ad5bb5d9a [jit_kernel] Move JIT kernels into namespace sglang (#33400) DarkSharpnessandClaude Fable 5 2026-08-08 16:10:15 +08:00
• 5fdf6cd18f [MoE] Single-launch moe_align for tiny batches with many experts (#32395) Yuan Luo 2026-08-08 16:08:25 +08:00
• 891445676c [diffusion] Sana: bit-exact fused aten LayerNorm+modulate under BCG (H200 denoise -4.8%) (#34015) Xiaoyu ZhangandClaude Fable 5 2026-08-08 16:05:25 +08:00
• d747bd052e feat(vlm): auto-select cuda vmm on multi-node mnnvl (#33936) Mick 2026-08-08 16:00:58 +08:00
• db3898fec1 fix: avoid piecewise prefill graph for trtllm_mla (#32785) Mick 2026-08-08 16:00:10 +08:00
• afb4f37ca5 [Inkling] silu_and_mul: replace helion kernels with plain Triton (#33903) Sam ShleiferandClaude Fable 5 2026-08-08 03:00:23 -04:00
• d238e36b24 [Fix] Restore data_parallel_rank alias on native /generate (dp-aware gateway routing is silently dropped) (#33565) Sam ShleiferandClaude Fable 5 2026-08-08 02:59:16 -04:00
• c9444deef4 Docker: install DeepEP from release wheels (#34041) Baizhou Zhang 2026-08-07 23:51:09 -07:00
• c69d59395b [inkling] Render tool-result media instead of coercing content to str (#33898) Eric ZhangandClaude Opus 5 2026-08-08 02:39:19 -04:00
• 6185ed8011 Add registered short-conv tests and backend extensions (#34045) Aurick Qiao 2026-08-07 23:38:03 -07:00
• 6679d9b60c [AMD] Add K3 verified mla kernel for DSpark on triton backend (#33981) Thomas Wang 2026-08-08 13:59:26 +08:00
• b61a06921e moe: the shared-experts-fusion decision is a per-runner value the loader installs (#33889) Cheng Wan 2026-08-07 22:42:58 -07:00
• eda0ddc260 config: delete the dead get_server_args() bindings across the repo (#33888) Cheng Wan 2026-08-07 22:41:53 -07:00
• a5af27f49e config: retire ServerArgs.derive; per-runner values are constructor arguments (#33887) Cheng Wan 2026-08-07 22:41:09 -07:00
• 5dffa06fe1 [diffusion] GLM-Image bit-exact fused aten LayerNorm+modulate / qk-LN (H200 30-step denoise -8.1%) (#34008) Xiaoyu ZhangandClaude Fable 5 2026-08-08 13:26:11 +08:00
• 148f15b0af [diffusion] FLUX.1 fused adaLN modulate (bit-exact) + RoPE cache hoist, LN-affine folding behind quality=high (H200 e2e -3.5% lossless / -6.9% high) (#34004) Xiaoyu Zhang 2026-08-08 13:07:42 +08:00
• f64328c7f6 [diffusion] feat: support quant-videogen prq kv-cache quantization (memory-saving) for causal-dit (#32581) 3 people 2026-08-07 21:56:54 -07:00
• 24c84dfa68 [diffusion] doc: add parallelism overview (#33704) MickandClaude Fable 5 2026-08-08 11:36:06 +08:00
• 55f02e6887 Support Intern-S2-Mobius (#33691) RunningLeonandXinyuan Tong 2026-08-08 11:06:57 +08:00
• a25c330eb1 [diffusion] feat: cross-node sequence parallelism (Ulysses x Ring) (#33327) MickandClaude Fable 5 2026-08-08 10:56:28 +08:00
• 52afe87a08 [diffusion] fix: stop runai-model-streamer's rank-discovery collective from firing on independent per-rank loads (#33969) MickandClaude Fable 5 2026-08-08 08:54:08 +08:00
• 209857334e [Scheduler] Gate SWA eviction on accumulated tokens (#33404) paulzhang-tm 2026-08-07 20:28:26 -04:00
• 633838b0ec Add the 8-gpu Inkling consistency test (#34009) Ke Bao 2026-08-08 08:24:08 +08:00
• ce84df0fa1 Fix deterministic inference for Inkling (#33417) Ke Bao 2026-08-08 07:48:15 +08:00
• 1d812865dc [Laguna] fix YaRN mscale double-application in rope config (#33558) Joe RowellandJimmy Shong 2026-08-08 01:46:08 +02:00
• c59d2b4329 [Fix] Judge the phase-checker device-assert test by its FAIL line, not the exit code (#34017) Liangsheng Yin 2026-08-07 16:19:05 -07:00
• 86f373daff docs(cookbook): DeepSeek-V4-Flash-0731 — drop chunked-prefill/autotune flags on B300 low-latency (#34044) Douglas YangandClaude Opus 5 2026-08-07 16:12:56 -07:00
• 3dc91366ac [HiCache] write_back: reclaim duplicated host copy first under host pressure (#33777) Zhiqiang Xie 2026-08-07 15:59:59 -07:00
• eb3cc879e0 Install DeepEP from release wheels (#33932) Baizhou Zhang 2026-08-07 15:38:44 -07:00
• 115cd7bde1 docs: update checkpoint to Qwen3.5 NVFP4 V2 for InfX (#32945) Faradawn Yang 2026-08-07 15:26:07 -07:00
• b2f9603f93 [bugfix] Stop/EOS inside a spec accept run beats the max_new_tokens finish (#33758) 4 people 2026-08-07 15:18:14 -07:00
• 07297049e9 config: route DCP topology reads through get_parallel() (#33925) Khoa PhamandClaude Opus 5 2026-08-07 14:53:54 -07:00
• df3aa20d89 Reland serving-time Triton load diagnostics (#33908) cctryandkangwangamd 2026-08-07 14:51:43 -07:00
• 8fc66d1a62 docker: pin Kimi images to SGLang commit (#34030) Baizhou Zhang 2026-08-07 14:49:26 -07:00
• 0da25ee6f7 Docs: Ling-3.0-flash cookbook — serve native 256K, drop YaRN override (#33882) Xinyuan Tong 2026-08-08 05:46:51 +08:00
• 8600457731 [Spec] Propagate state capture outputs in DFlash (#34026) Nan Jiang 2026-08-07 14:42:30 -07:00
• 9e3f6b746b fix(mamba): widen causal_conv1d token offsets to int64 (#33665) YAMY 2026-08-07 14:31:48 -07:00
• b3ee679467 [MXFP8] Use FlashInfer CUTLASS for dense GEMM on SM120, delete Triton path (#33208) Brayden ZhongandBrayden Zhong 2026-08-07 14:30:43 -07:00
• 699fcdc936 Fix _pa_swa_prefill_lens off-by-one in FlashAttentionBackend (#33379) Dmitrii Sergeev 2026-08-08 00:06:48 +03:00
• 62a28197c0 Autotune flashinfer extend buckets at warmup (#32556) Sam ShleiferandClaude Fable 5 2026-08-07 17:06:05 -04:00
• 1480687cff [CP]: Support CP V2 Strategy for dsv4 (#33532) Zhangheng 2026-08-08 05:03:27 +08:00
• 8e7d361def [perf] Compute input logprobs without materializing the full-vocab log-softmax (#31958) Sam Shleifer 2026-08-07 17:01:08 -04:00
• 8a22b8305d docker: add Kimi K3 artifacts and build hpc-ops with C++20 (#33956) Baizhou Zhang 2026-08-07 13:50:44 -07:00
• b53a39c5e4 Limit prefill delayer debug logs to rank zero (#34020) Hanming LuandLianmin Zheng 2026-08-07 13:41:19 -07:00
• 7f6b4cb94b Add CUDA VMM multimodal feature transport (#33899) Oguz UlgenandYinghai Lu 2026-08-07 13:39:54 -07:00
• 3c51e29deb Responses support (#32689) 7 people 2026-08-07 13:21:46 -07:00
• 6c7498113f [diffusion] Enable breakable CUDA graph for SANA (H200 1024px e2e -26%, bit-exact) (#33989) Xiaoyu ZhangandClaude Fable 5 2026-08-07 23:54:39 +08:00
• 12de7fb1f6 Remove the HiMambaRadixTree that is no longer in use (#33468) Zhangheng 2026-08-07 23:01:40 +08:00
• d4be483efb [diffusion] Enable breakable CUDA graph for LTX-2 (H200 two-stage e2e 10.75 s -> 6.90 s, 1.56x) (#33885) Xiaoyu Zhang 2026-08-07 22:29:14 +08:00
• bc148dfdc8 [diffusion] feat: make scheduler rpc deadlines explicit (#33965) 3 people 2026-08-07 21:33:23 +08:00
• bc8c037041 Fix vae fast path test after the gate refactor (#33983) Ke Bao 2026-08-07 20:45:19 +08:00
• 4020bc95a7 Fix Nemotron W4A16 NVFP4 MoE backend (#33543) danielafrimi 2026-08-07 15:00:28 +03:00
• 5ca734fc3d [diffusion] UX: speed up tp and fsdp checkpoint loading (#33960) Mick 2026-08-07 19:23:30 +08:00
• 1034977318 [diffusion] fix: bind each rank to accelerator before distributed init (#33054) Dayananda V 2026-08-07 16:31:58 +05:30
• acb64db9e2 [diffusion] fix: enable bcg with tp (#33421) Yihao WangandClaude Opus 5 2026-08-07 04:01:05 -07:00
• fe52b49827 Fix IndexError in Triton backend with pipeline parallelism (#30340) 3 people 2026-08-07 16:28:04 +05:30
• 7af3d000f2 [diffusion] feat: gate /health and /health_generate on warmup completion and add liveness endpoint (#33787) Lennox FuandMick 2026-08-07 02:59:23 -07:00
• a42683eb62 [diffusion] model: support lingbot-video moe 30b t2v (#32341) Pan LiandMick 2026-08-07 17:57:01 +08:00
• 13938fed3f [diffusion] feat: make ring admission a backend capability (#33928) MickandClaude Fable 5 2026-08-07 17:55:44 +08:00
• 28b43bf693 [diffusion] perf: build qwen's masked varlen metadata host-side (#33954) MickandClaude Fable 5 2026-08-07 17:55:15 +08:00
• 0756a1d2b0 Move SWA chunk-cap hatch tests into the registered suite (#33975) Ke Bao 2026-08-07 17:49:07 +08:00
• 470807ef74 [NPU] [DOC] Upgrade recommendeded sglang version on Ascend NPU (#33976) amote-i 2026-08-07 17:45:00 +08:00
• 572434e2f6 [diffusion] Z-Image bit-exact fused qk-norm (H200 Turbo 1024px e2e -6.4%) (#33886) Xiaoyu ZhangandClaude Fable 5 2026-08-07 17:03:28 +08:00
• 5e60363960 Fix prefill CP graph overflow with larger bucket search (#33906) Baizhou Zhang 2026-08-07 01:33:14 -07:00
• 7395ee833e [CI] Share VLM engines and prune launch matrices on the per-commit H100/H200 suites (#33944) Liangsheng Yin 2026-08-07 01:22:22 -07:00
• 3ed2a0adf3 feat: Add flashinfer mHC fusion for DSV4 (#33616) Trevor Morris 2026-08-07 01:01:33 -07:00
• 85d611a055 [diffusion] fix: scope the masked-path replicated guard to sp runs (#33953) MickandClaude Fable 5 2026-08-07 15:45:50 +08:00
• 5e58af1503 Fix fractional simulated acceptance in DSpark (#33463) weireweireandweireweire 2026-08-07 15:45:07 +08:00
• 9aadacfc53 [diffusion] CI: exercise the default sp selection in CI (#33931) Mick 2026-08-07 14:20:19 +08:00
• a79340dedd [diffusion] fix: minimax-h3 text encoder device mismatch under --text-encoder-cpu-offload (#33864) triple-mu 2026-08-07 14:04:20 +08:00
• fc9479243e [AMD][DI][CI] 8/N Add GLM-5.2 MXFP4 1P1D DI/CI recipes (base + MTP + DP8/EP8) (#32120) Zhaoyi Li 2026-08-07 00:56:40 -05:00
• 4d4f8023c4 [srt] Batch scheduler cache frees (#33475) Leon Gao 2026-08-06 21:49:59 -07:00
• c2657cc4bf [diffusion] refactor: gate fast vae paths by quality (#33849) Mick 2026-08-07 12:39:55 +08:00
• 914644e81c [diffusion] fix: fix 4/8-step distilled minimax-h3 turbo lora merge (#33875) WenhaoZhang 2026-08-07 12:38:37 +08:00
• 6dc77e490d [diffusion] chore: route zimage and hunyuanvideo attention through USPAttention (#33923) MickandClaude Fable 5 2026-08-07 12:36:23 +08:00
• 698f019a5a [diffusion] chore: derive h3 attention admission from backend capabilities (#33707) MickandClaude Fable 5 2026-08-07 12:35:15 +08:00
• afa79330b8 [misc] Remove break-graph debug log; reclaim pid-less /dev/shm leaks in CI (#33929) Liangsheng Yin 2026-08-06 21:18:01 -07:00
• 0c3a76fa0a Clean GLM-5.2 NVFP4 cookbook (#33935) Brayden ZhongandBrayden Zhong 2026-08-06 20:51:34 -07:00