Commit Graph
6055 Commits
Author SHA1 Message Date
McZyWu 69a49fede8 fix(kimi-k3): preserve dense ModelSlim MLA weights (#36603) 2026-08-28 02:15:52 -07:00
Zheng Wengang 1e6d041f78 [BugFix][VLM] keep Qwen3-VL MoE inference deepstack order (#34690) 2026-08-28 17:02:16 +08:00
Zhiqiang Xie 3785b2d20f [HiCache] Reject load-back specs that claim nodes pinned by an in-flight load-back (#35931) 2026-08-28 01:59:06 -07:00
Xiaoyu Zhang eebb99c049 [diffusion][kernel] avoid 4D scale-shift autotuning (#36521) 2026-08-28 16:58:19 +08:00
Xiaoyu Zhang 45424d8434 [diffusion][kernel] support transposed residual-gate add (#36504) 2026-08-28 16:54:37 +08:00
Zhiqiang Xie 1061e34785 [HiCache] Retry L3 storage prefetch after a missed attempt (#36227) 2026-08-28 01:35:21 -07:00
Yikai Zhangandamdpilot-upstream-sync d3b972cbf0 fix(lora): build the MoE LoRA align JIT kernel on ROCm (#36379)
Co-authored-by: amdpilot-upstream-sync <amdpilot-upstream-sync@users.noreply.github.com>
2026-08-28 01:18:42 -07:00
Bingxu Chen 2a7fb511c9 [AMD][CI] Limit HiCache MGSM eval concurrency on ROCm (#36308) 2026-08-28 01:05:59 -07:00
Thomas Wang baf09f3954 [AMD] Enable deepseek-v4 topk_transform v2 kernel (#36684) 2026-08-27 22:36:11 -07:00
Xinyuan Tong 0665102ce5 [Fix] Resolve tool argument types through top-level anyOf/oneOf/allOf (#36626) 2026-08-27 21:50:30 -07:00
2380121e9b [HiCache] Stop populating host-pool mmaps twice (-13% allocation time) (#36705)
Co-authored-by: DellCurry <30748980+DellCurry@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-28 11:54:11 +08:00
karverma-amd 2b209711d8 [AMD][DSV4] perf: MXFP8 MoRI dispatch to match the w4a8 MoE input format (#36119) 2026-08-27 20:45:40 -07:00
YAMY 6480cce9bc perf: skip redundant scheduler metadata gather for DP1 (#36568) 2026-08-27 20:04:54 -07:00
Liangsheng Yin daf6317196 [mem_cache] Add free_full to release the full side of a tombstoned SWA node (#36637) 2026-08-27 19:34:48 -07:00
pllimax 22f37d414b [NPU] Chain PR test jobs and disable two DeepSeek-V4-Flash perf tests (#36672) 2026-08-28 09:16:09 +08:00
Xiaoyu Zhang 96b31770f9 [diffusion] fuse Helios paired transposed RoPE (#36502) 2026-08-28 08:57:37 +08:00
Aurick QiaoandYuwei An 26fd7fdaa2 [Feature] Support PP in full prefill CUDA graphs (#35451)
Co-authored-by: Yuwei An <ayw.sirius19@gmail.com>
2026-08-27 17:32:00 -07:00
ashwini rathi 7cbe564829 [Fix][XPU/ROCm/NPU] Defer sgl_kernel.quantization import in expert_pack (#36529) 2026-08-27 16:17:24 -07:00
Cheng WanandClaude Opus 5 6ff2a20ccf config: the record is not an object that gets passed around (#36622)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-27 12:57:10 -07:00
Cheng WanandClaude Opus 5 fd40a331bf config: a parallel size has one spelling; a patched scope declares its own (#36621)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-27 12:56:42 -07:00
Cheng WanandClaude Opus 5 ca1d7ed8e6 config: a parallel leaf with no live counterpart is read bare (#36620)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-27 12:56:11 -07:00
Cheng WanandClaude Opus 5 7c3b5a6732 config: every handler declares its cuda-graph decisions (#36725)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-27 12:55:34 -07:00
Cheng WanandClaude Opus 5 bd4bb1781a config: resolution declares, and nothing writes a field (#36618)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-27 12:53:17 -07:00
Lianmin Zheng a0a2295271 Refactor server_args constants and layout (#36676) 2026-08-27 12:16:16 -07:00
Mickandjohn.xh 20a491d1d3 [Fix] Re-encode multimodal embeddings after cache mismatch (#36595)
Co-authored-by: john.xh <dengxuhuijohn@gmail.com>
2026-08-27 23:24:30 +08:00
97ba99067d Publish per-scheduler load on a dedicated socket for load-aware routers (#34608)
Co-authored-by: Kangyan Zhou <zky314343421@gmail.com>
Co-authored-by: Zhangheng <hzh0425@apache.org>
2026-08-27 19:33:18 +08:00
Lianmin Zheng 94183a8d2b Move server args config parser under utils (#36681) 2026-08-27 03:34:50 -07:00
Xiaoyu Zhang ad911a5ec0 [kernel] Tune LingBot-Video MoE TMA configs for H100 (#36543) 2026-08-27 02:47:32 -07:00
Schwinn Saereesitthipitak 08315c56df [Fix] Account resident weight memory in KV sizing (#34053)
Signed-off-by: Schwinn Saereesitthipitak <schwinns@nvidia.com>
2026-08-27 02:43:04 -07:00
Xia Weiwen 56fdfc3b26 XPU: remove SGLANG_USE_SGL_XPU flag (#34492) 2026-08-27 02:38:02 -07:00
Lianmin Zheng 3402265989 [Core] Refactor server argument choices (#36586) 2026-08-27 01:56:03 -07:00
Alison Shao a126a5fa31 [CI] Graceful teardown for the radix_cache server fixtures (#36605) 2026-08-27 16:36:04 +08:00
MickandClaude Opus 5 c2c3320cf0 [VLM] feat: size the multimodal preprocessing pool by where preprocessing runs (#35349)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-27 16:32:58 +08:00
Po-Han Huang (NVIDIA) c608f9bf75 [CI] Fix Q8KV8 sparse prefill test fixture (#36639) 2026-08-27 01:00:22 -07:00
b8a6adadfe [Bug][Spec] fix startup crash and reduce CUDA graph memory usage for speculative adaptive (#35275)
Co-authored-by: alphabetc1 <2508695655@qq.com>
Co-authored-by: Shuwen Wang <47200617+alphabetc1@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-27 00:46:13 -07:00
jacky.cheng c967cd19b5 [AMD] Optimize Qwen3.5 MTP unified attention on gfx950 (#36330) 2026-08-27 00:13:49 -07:00
Xun Sun adcf73d7f7 [Weight Cache] Enhance test and support EPLB (#36198) 2026-08-26 23:11:53 -07:00
b294bd4bc7 [CPU][CI]: fix a few issues that cause XEON CI failures (#36413)
Co-authored-by: Zhang, Mingxu <mingxu.zhang@intel.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: MingxuZh <109504044+MingxuZh@users.noreply.github.com>
2026-08-27 13:59:08 +08:00
weireweireandweireweire 4d5d506486 Publish gated DSV4 DFLASH-family target-prefill read completion (#35947)
Co-authored-by: weireweire <20922698+weireweire@users.noreply.github.com>
2026-08-26 21:33:08 -07:00
Alison Shao 02dfd37826 [CI] Remove GLM-4.1V-9B-Thinking from nightly VLM MMMU eval (#36602) 2026-08-26 20:29:38 -07:00
Jialin Ouyang a2b589fdf8 [Radix Cache] Add test-only TreeCore inspector for shared backend tests (#35791) 2026-08-27 11:17:51 +08:00
a3ae667d67 [Feature] Add DeepEPv2 (ElasticBuffer) MoE A2A backend (#35634)
Co-authored-by: menyu <menyu@nvidia.com>
Co-authored-by: Jinyan Chen <93358689+liz-badada@users.noreply.github.com>
Co-authored-by: Han Yu <helloyu0903@gmail.com>
Co-authored-by: Cheng Wan <cheng.wan@radixark.ai>
2026-08-26 19:54:33 -07:00
Michael 1c8f2b38cb [AMD][CI] Add DeepSeek-V4-Flash FP8 accuracy coverage on MI30x (#36396) 2026-08-26 19:30:07 -07:00
MickandClaude Opus 5 07570202f0 [VLM] route every multimodal processor through the worker pool's call site (#35342)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-27 10:27:45 +08:00
Promisewjx 9d07b9e227 [Performance] Reduce idle DP work in breakable prefill CUDA graphs (#33871) 2026-08-27 10:09:54 +08:00
Bingxu Chen d2b3e9051d [AMD][CI] Stabilize PyTorch sampling backend test on ROCm (#36307) 2026-08-26 18:44:10 -07:00
Alison Shao 15688fea7d Fix BailingMoeV3 reading enable_dp_lm_head off live topology instead of config (#36584) 2026-08-26 18:41:39 -07:00
ashwini rathi a8b72c4c34 [Intel XPU] Fix cross-encoder rerank hang on B580 runners (#36360) 2026-08-27 09:33:20 +08:00
20621aa14b [Model] Support Ling-3.0-flash (BailingMoeV3) (#33561)
Signed-off-by: JustinTong <justintong0323@gmail.com>
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
Co-authored-by: 得泽 <zhangkaihong.zkh@antgroup.com>
Co-authored-by: 翎悦 <vito.yy@antgroup.com>
Co-authored-by: 羽癫 <yudian.zy@antgroup.com>
Co-authored-by: tiwei.btw <tiwei.btw@antgroup.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
Co-authored-by: 文赋 <zibin.zb@antgroup.com>
Co-authored-by: JustinTong <justintong0323@gmail.com>
2026-08-26 17:27:23 -07:00
ec4bdbfa4a [Feature] Beam search support (#31626)
Co-authored-by: cswuyg <cswuyg@gmail.com>
Co-authored-by: cswuyg <496090217@qq.com>
Co-authored-by: Vedant Jhaveri <vedantjh2@gmail.com>
Co-authored-by: Vedant Jhaveri <vjhaveri@linkedin.com>
2026-08-26 16:56:15 -07:00