Commit Graph
13023 Commits
Author SHA1 Message Date
Kangyan-Zhou 63ecf2f62b [CI] Drop unused 'environment: prod' from bot-cherry-pick job (#26067) 2026-05-22 16:16:07 +08:00
siyu 06836aa38a update code owner (#26060) 2026-05-22 16:13:28 +08:00
jiayisunx 6339295556 [XPU] add apache-tvm-ffi dependency (#26053) 2026-05-22 16:09:08 +08:00
zijiexiaandClaude Opus 4.7 88a37d7405 [docs] DeepSeek-V4 cookbook: split Quantization axis, add H100 SGLang FP8 (#26057)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-22 00:52:10 -07:00
Yuhao YangandKe Bao c9153da5dc Fix SWA double-free in disagg decode with MTP speculation (#25805)
Co-authored-by: Ke Bao <ispobaoke@gmail.com>
2026-05-22 00:28:54 -07:00
Chi McIsaac a7555fc997 [diffusion] fix: fix MOVA DAC bf16 on ROCm (#25674) 2026-05-22 15:18:49 +08:00
Liangsheng Yin c4b6b5ea1e [core] step 2: drop seq_lens sentinel; SB maintains GPU as seq_lens_cpu mirror (#26020) 2026-05-22 00:12:51 -07:00
Yuhao YangandYaochen Han fa6f4dfb35 improve: combine vit calls for images from different reqs from one batch (#25910)
Co-authored-by: Yaochen Han <814073252@qq.com>
2026-05-22 14:57:41 +08:00
fzyzcjy 3f0814974c Fix disaggregation bootstrap server lifetime (#25982) 2026-05-22 14:10:57 +08:00
Khoa PhamandClaude Opus 4.7 f829cafa3e [perf] skip add_special_tokens=False kwarg on chat-template tokenize for slow tokenizers (#25953)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-21 22:45:54 -07:00
Liangsheng Yin acb8310183 ci: self-heal $GITHUB_PATH/$GITHUB_ENV writes (#26037) 2026-05-21 21:28:43 -07:00
ybyang 610f55040d update npu codeowners (#26042) 2026-05-21 20:46:59 -07:00
Alex O. P. ae7c4226eb [diffusion] model: support FLUX.2-klein-base (#25661) 2026-05-22 11:24:46 +08:00
Liangsheng Yin 8b473aa0bc [core] step 1: route non-spec seq_lens via FutureMap with per-mode bootstrap fixes (#25944) 2026-05-21 20:15:51 -07:00
jianzhao-xu cc77c36029 Bugfix: Qwen3-VL-MoE adapt encoder_only (#23220) 2026-05-22 11:12:13 +08:00
Mohammad Miadh Angkad 76b1efaffd Fix SMG service discovery Clippy lint (#26034) 2026-05-22 10:51:13 +08:00
Liangsheng Yin 7c02ca7882 cancel pr ci: cover closed-no-merge; widen workflows; rerun-test opt-in (#26035) 2026-05-21 19:38:24 -07:00
longguoandYang 4374789abf fix(mm): make multimodal data loading non-blocking to prevent health check stalls (#24751)
Signed-off-by: abinggo <107740309+abinggo@users.noreply.github.com>
Co-authored-by: Yang <ID+Y-aang@users.noreply.github.com>
2026-05-22 10:08:03 +08:00
McZyWu b2631a9a4d [NPU] Docs op performance optimize (#25830) 2026-05-22 09:20:13 +08:00
Mick 16b3edc84f [diffusion] feat: enable warmup for sglang serve by default (#25988) 2026-05-22 08:54:48 +08:00
Mick f6d98a17ba [diffusion] optimize: reuse cached dynamic lora weights (#25893) 2026-05-22 08:54:01 +08:00
nohup 7cf193fe1f feat: support HybridLinearKVPool in chunked prefix cache handling (#25753) 2026-05-21 16:17:26 -07:00
Cheng WanandClaude Sonnet 4.6 d765dfd043 refactor(attn): init hisparse_coordinator before attn_backend; replace lazy property with init-time capture (#26012)
Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-05-21 16:03:42 -07:00
Cheng WanandClaude Sonnet 4.6 c5251a98a9 feat(model_runner): remove pool/backend refs from ForwardBatch via ForwardContext (#25983)
Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-05-21 14:01:49 -07:00
Liangsheng Yin 44ec2ee18d [core] Unify output_tokens_buf in FutureMap (#25922) 2026-05-21 13:56:44 -07:00
Liangsheng Yin c9a0e55eb5 [Spec] Polish FutureMap after #25879: rename callback, async guard, cleanup (#25962) 2026-05-21 13:56:22 -07:00
zijiexiaandClaude Opus 4.7 17dadebd4e [Docs] DeepSeek-V4: switch H200 FP4 Pro to flashinfer_mxfp4, Flash Balanced too (#25923)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-21 13:51:40 -07:00
Jimmy Shong 1a85586738 [Fix]: Restrict Kimi-K2.5 shared-experts fusion to Quark MXFP4 checkpoints (#25974) 2026-05-21 13:07:45 -07:00
Yuhao Yang 81d686d9fa Default MegaMoE to W4A8 for Max-Throughput recipe (#26004) 2026-05-21 11:54:16 -07:00
Cheng WanandClaude Opus 4.7 b765faee30 [MoE Refactor] deprecate forward_npu and NpuFuseEPMoE (#25678)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-21 10:25:17 -07:00
Ethan (Yusheng) SuandCursor a24c374f84 [lora] Remove synchronous .any().item() guard in LoRA MoE prefill path (#25531)
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-21 23:58:57 +08:00
Mick ca9dc17be4 [diffusion] chore: adjust layer wise-offload strategy (#25930) 2026-05-21 23:48:58 +08:00
Kangyan-ZhouandClaude Opus 4.7 049bb83134 [CI] bot-cherry-pick: surface created PR number/URL in job summary (#26001)
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-21 22:58:21 +08:00
liuxianglong17 32f996b75a Avoiding the problem of printing a large number of compatibility warn… (#25956) 2026-05-21 22:10:23 +08:00
Kangyan-ZhouandLiangsheng Yin caa9f08294 [CI] Force-reinstall nvidia-cutlass-dsl-libs-cu13 last to avoid wheel-mix TypeError (#25958)
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
2026-05-21 22:01:42 +08:00
amote-i ac83d8a339 docs: delete deprecated args from npu supported features (#25995) 2026-05-21 20:20:29 +08:00
Kangyan-Zhou 32352f7edf [CI] Fix bot-cherry-pick: use state == "MERGED" instead of invalid merged field (#25987) 2026-05-21 20:10:12 +08:00
Shangming Cai fbebdd5105 [CI] Enable nixl disaggregation test for decode radix cache (#25990) 2026-05-21 19:29:24 +08:00
loading66 2e0d2d4c18 [NPU][DOCS]Add best practice and benchmark result parameter description (#25875) 2026-05-21 19:08:10 +08:00
Kangyan-Zhou 64f21b1589 [CI] Improve bot-cherry-pick: accept PR number, require merged, explicit title (#25981) 2026-05-21 18:32:57 +08:00
8562d5ae94 [AMD] Relaxing Timeout for AMD stage-a (#25978)
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Bingxu Chen <Bingxu.Chen@amd.com>
Co-authored-by: bingxche <bingxche@amd.com>
2026-05-21 17:32:51 +08:00
jianzhao-xu f66881f03c [NPU]Ascend NPU Performance Profiling Guide and Ascend NPU Operator Development Guide (#25384) 2026-05-21 17:32:25 +08:00
Bingxu ChenandCursor e72e3145a0 [AMD] Upgrade AITER (#25896)
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-21 02:10:43 -07:00
Liangsheng Yin baeac179f7 [Spec] Route seq_lens through FutureMap; drop verify_done.wait (#25879) 2026-05-21 01:51:40 -07:00
DarkSharpnessandClaude 19f55c0e6d [Refactor] major JIT kernel clean up for dsv4 (#25884)
Co-authored-by: Claude <noreply@anthropic.com>
2026-05-21 01:14:31 -07:00
Liangsheng Yin 1b3d8da827 cap API quota for runner-utilization / amd-ci-job-monitor (#25965) 2026-05-21 01:13:37 -07:00
hxie c3f9bc9818 Fix nixl mla key and backup skipping (#24376) 2026-05-21 00:48:28 -07:00
看海的人 b9ae8353d2 [NPU] Support model DeepSeek-OCR and DeepSeek-OCR-2 (#25257) 2026-05-21 15:21:20 +08:00
Liwansi 190488e9a8 [NPU] Support chunk prefill for Qwen3.5/Qwen3.6 models (#25839) 2026-05-21 14:44:25 +08:00
Kangyan-Zhou 4ea8282cb7 [Revert] nvidia-cutlass-dsl[cu13] 4.5.1 -> 4.5.0 (#25938) 2026-05-21 14:36:56 +08:00