Commit Graph
20367 Commits
Author SHA1 Message Date
cen121212 9305d10099 [NPU] adapt_fused_rope_qk_mqa_optimize (#28872) 2026-06-25 08:55:52 +08:00
fzyzcjy d0524d6433 Avoid scattered assignment of extend_input_len and fill_len by merging them into Req.extend_range (#27610) 2026-06-25 08:33:28 +08:00
Lianmin Zheng 6c839368e0 [Cleanup] IPC struct renames, better typing, and SenderWrapper removal (#29214) 2026-06-24 17:25:24 -07:00
fzyzcjy 563c3418a7 Avoid dual semantics of extend_input_len by computing the candidate on the fly (#27616) 2026-06-25 08:17:37 +08:00
Brayden ZhongandBrayden Zhong 5d4e63d49e Sync the changes in #23402 (#29063)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
2026-06-24 17:01:02 -07:00
Brayden ZhongandBrayden Zhong f82addd4a8 Support online MXFP8 quantization for ungated MoE (#27939)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
2026-06-24 16:58:48 -07:00
Jiajun LiandClaude Opus 4.8 e4bf0043fe [fix] Skip routed expert capture for draft model under spec v2 (#26980)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 16:56:07 -07:00
Lianmin ZhengandYinghai Lu 7e63feee6f Add scheduler metrics extension hooks (#29207)
Co-authored-by: Yinghai Lu <yinghai@meta.com>
2026-06-24 15:50:05 -07:00
Qiaolin Yu e26bceb81e [perf] simplify _apply_cuda_graph_metadata for draft extend in trtllm_mla backend (#29077) 2026-06-24 15:45:26 -07:00
Liangsheng Yin 85a3f1f75c [Spec] Unify the overlap stash relay behind a RelayPayload dataclass (#29124) 2026-06-24 15:36:54 -07:00
Liangsheng Yin c6822f81b1 [Spec] Make the overlap bonus-token relay unconditional (#29122) 2026-06-24 15:34:02 -07:00
Liangsheng Yin d3dd184e3e [Spec] Fold DFlash verified_id into the shared bonus_tokens relay channel (#29118) 2026-06-24 15:30:29 -07:00
Brayden ZhongandBrayden Zhong 3c95a87b66 Fix the CuDNN failure on bmm_fp8 when two libcudart.so exists. (#29201)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
2026-06-24 15:26:46 -07:00
weireweireandweireweire 5f30fa258c Support DP-aware PD router dispatch (#26245)
Co-authored-by: weireweire <20922698+weireweire@users.noreply.github.com>
2026-06-24 15:02:51 -07:00
Lianmin ZhengandRain Jiang fd87a85388 Convert SamplingParams to msgspec Struct (#29198)
Co-authored-by: Rain Jiang <96632942+rainj-me@users.noreply.github.com>
2026-06-24 13:42:45 -07:00
Kaixi d5e9176f65 [BCG][GLM5] perf: BCG support and prefill enhancements (#27053) 2026-06-24 13:13:35 -07:00
Brayden ZhongandBrayden Zhong d46afbf8b4 Fix nightly CI test for GLM-4.6 + B200 (#28749)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
2026-06-24 12:34:11 -07:00
Qiaolin Yu c01ad10d16 [perf] tiny optimize select_index op for draft extend (#29078) 2026-06-24 12:27:13 -07:00
Brayden ZhongandBrayden Zhong 2c697daf5f [Cookbook] Nemotron3-Ultra: align MTP draft depth with NVIDIA reference (num_steps 5) (#29200)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
2026-06-24 19:12:34 +00:00
Anusha Pant e97cc339e3 Add DeepSeek V4 Flash demo notebook (#28952) 2026-06-24 18:42:33 +00:00
Lianmin Zheng d5c566e59b Extract profile request cleanups (#29098) 2026-06-24 11:22:58 -07:00
Lianmin ZhengandCheng Wan d6aacd2801 Handle input-embed-only batches in eager runner (#29121)
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
2026-06-24 10:33:52 -07:00
cctryandcctry 76db6c9d9e [Refactor] Share CUDA graph memory pool across prefill and decode (#28973)
Co-authored-by: cctry <cctry@fb.com>
2026-06-24 10:18:20 -07:00
Yihao Wang dd4caf9459 [Docs] fix SGLang-diffusion installation links (#29139) 2026-06-24 09:46:06 -07:00
Mick 4a4f063b79 [diffusion] fix: paint multiview vae must follow unit dtype (#29041) 2026-06-24 23:54:01 +08:00
qiaozpandishandhanani 03773ae35b [HiCache] Add NIXL FILE cache cleaner (#28258)
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
2026-06-24 08:13:55 -07:00
Mick 09b808ab7e [diffusion] fix: fix Qwen-Image-Layered latent shape (#28832) 2026-06-24 20:57:54 +08:00
nvjullin 84a7a84018 [PD] Fix data race in NixlKVManager for NIXL backend (#28897) 2026-06-24 18:11:01 +08:00
hirakunaramuka2andClaude Fable 5 7430c56b20 [Misc] Use logger instead of print() in utils/common.py (#29004)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-06-24 09:45:01 +00:00
zhaozx-cn 10e0bcd622 [NPU] fix dcp break (#29140) 2026-06-24 17:33:02 +08:00
amote-i 73d976e375 [NPU] [DOC] Fix TOC of Ascend NPU Docs (#29129) 2026-06-24 16:47:10 +08:00
Mohammad Miadh Angkad 4992f7a108 Fix TRTLLM MHA FP8 KV cache scale handling (#28144) 2026-06-24 01:43:50 -07:00
Yuhao Yang 0fc815aa2c [CI] Temporarily disable openbmb MiniCPM tests (#29095) 2026-06-24 01:39:44 -07:00
Liangsheng Yin 8e1988b746 [Perf] Overlap result D2H copy with the next forward step (#29075) 2026-06-24 01:34:02 -07:00
jundu e04ed05193 [CI] reduce CPU CI scope with base-c suite (#28623) 2026-06-24 16:18:06 +08:00
Even Zhou 4da23fdc35 [NPU] removes deprecated pr testing files (#27859) 2026-06-24 16:06:45 +08:00
zijiexiaandClaude Opus 4.8 dd2d919e21 [Docs] Fix mem-fraction-static default and document how it is computed (#29135)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-24 08:05:06 +00:00
Even Zhou 39f5de9ba1 [NPU] bump sgl-kernel-npu to 2026.6.2 (#29101) 2026-06-24 15:59:41 +08:00
Tai An 00eac7ec9b [diffusion] fix: disable proxy env in warmup health probe (#28503) 2026-06-24 15:58:44 +08:00
zijiexiaandClaude Opus 4.8 a707b2054d [CI] Fix pre-commit failures in MLX backend tests (#29141)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-24 15:56:52 +08:00
5f76736427 kimik2_detector fix the normal text detection before tool call. (#25071)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Rohit Harkhani <rharkhani@gmail.com>
2026-06-24 15:53:22 +08:00
weibingoandZhangheng b6a8000473 [bugfix][decode hicache] _storage_hit_query use HybridPrefetchOperation (#28422)
Co-authored-by: Zhangheng <hzh0425@apache.org>
2026-06-24 15:13:48 +08:00
silencejade 6c6fa19a90 [NPU] Support fsdp for rl_on_policy_target (#29128) 2026-06-24 14:57:19 +08:00
Xiaoyu Zhang 26e1d4d847 [KDA-Pilot] Add B200 diffusion norm-scale-shift CUDA fast path for Qwen-Image (#27392) 2026-06-24 14:38:36 +08:00
Yuan Luoandluoyuan.luo 0df796473b [VLM] Qwen3-VL / Moss-VL ViT preprocessing optimizations (#28940)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
2026-06-24 14:36:29 +08:00
Xiaoyu Zhang 534ac98eb2 [codex] Optimize DMD Wan auto residency on high-memory GPUs (#28780) 2026-06-24 14:03:23 +08:00
Stella-17andxinyue.fan 6842335fcf [MUSA][24/N] CI:Fix LLM server smoke test (#28934)
Co-authored-by: xinyue.fan <xinyue.fan@mthreads.com>
2026-06-23 22:58:59 -07:00
toufupiand“toufupi” c394f812d1 [MLX] Fix Apple Silicon server startup; align MLX tests with upstream (#28770)
Co-authored-by: “toufupi” <“byte2016@outlook.com”>
2026-06-23 22:58:49 -07:00
Yihao WangandClaude Opus 4.8 5beddc8afc [Diffusion] Add Krea 2 support (#29052)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-23 22:56:51 -07:00
Tarushii Goel 24bf8d91bb Refactor / simplify MultiLayerEagleDraftExtendCudaGraphRunner to use rotation (#28492) 2026-06-23 22:36:47 -07:00