Commit Graph
4261 Commits
Author SHA1 Message Date
Cheng WanandClaude Opus 5 a43592dce5 config: pin two orderings resolution relies on (#35909)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-23 01:19:44 -07:00
Cheng WanandClaude Opus 5 362c2ee849 config: borrowed-record reads follow the config bags (#35908)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-23 01:19:20 -07:00
Cheng WanandClaude Opus 5 64aa859da2 config: constructing a config no longer resolves it (#35907)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-23 01:18:53 -07:00
Cheng WanandClaude Opus 5 4bc79a1b49 config: project the config bags from the resolution result (#35906)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-23 01:18:24 -07:00
Cheng WanandClaude Opus 5 0e22777572 config: record resolution writes in a declaration stash (#35905)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-23 01:17:27 -07:00
Cheng Wan 6218d6ce3f config: a defensive publish must not re-project over a live process (#35904) 2026-08-23 01:16:39 -07:00
Xinyi Song edd675cecf [AMD] Add Radix-4 MoE top-k router kernel for Kimi-K3 routing (#34490) 2026-08-22 23:57:35 -07:00
Chungman LeeandMohammad Miadh Angkad 7f30d66045 [Kimi-K3] Fix "wrong grids" crash in DP-sharded vision preprocessing (#35305)
Co-authored-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
2026-08-23 09:20:51 +08:00
Hồ Sỹ Thế eec794bce0 [AMD][Spec] Fix aiter GQA packing + split-KV routing in NEXTN spec attention (verify & draft_extend) (#30105) 2026-08-22 14:22:43 -07:00
d315eb7250 [AMD] DeepSeek-V4: add aiter fused mHC post+pre with cross-layer boundary dispatch (#32577)
Co-authored-by: 1am9trash <1am9trash@gmail.com>
Co-authored-by: HAI <hixiao@gmail.com>
2026-08-22 07:34:57 -07:00
Shangming Cai 3c69a4c744 fix(test): unbreak test_kv_transfer_replica_metric after #35950 (#35974) 2026-08-22 19:23:46 +08:00
siyuandliusy58 cb10ca16dd [FEAT] Weight Daemon abstraction (#33279)
Co-authored-by: liusy58 <liusy58@smail.nju.edu.cn>
2026-08-22 02:13:46 -07:00
Mohammad Miadh Angkad 90354326c7 [VLM] Split Pixtral multi-image features before the CUDA IPC wrap (#35463) 2026-08-22 15:17:55 +08:00
Jianfei Wangandmiraclezqc af39ad9349 [Model] Complete dots.note.omni support with native encoders, video preprocessing, and MTP decoding (#33829)
Co-authored-by: miraclezqc <dysania@pku.edu.cn>
2026-08-22 14:19:14 +08:00
Xiaoyu Zhang 83e9ece672 [diffusion] Fuse SANA-Video interleaved RoPE (#35695) 2026-08-22 12:56:45 +08:00
Mohammad Miadh AngkadandMohammad Angkad 3e096629cf [CI] Re-enable B300 jobs (#35607)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-08-22 12:34:21 +08:00
Shangming Cai ac179eec11 fix(disagg): PD transfer-failure injection was silently inert (#35890) 2026-08-22 11:51:16 +08:00
Zhiqiang Xie 0db2bdfec5 Fix buffer-mode HiCache load-back ownership races; add optional prefetch anchor lock (#35769)
Signed-off-by: Zhiqiang Xie <zqx@meta.com>
2026-08-21 20:20:36 -07:00
Alec SandAlec Solder fbafd1b123 Add sampling observer auxiliary output hooks (#35747)
Co-authored-by: Alec Solder <alecs@fb.com>
2026-08-21 19:28:18 -07:00
Ke Bao 5662c03363 Support CPU offload for mxfp8 KV cache (#35888) 2026-08-22 10:19:06 +08:00
R0CKSTARandAlex Nails d90318b3e2 [MLX] Upgrade to Torch 2.13/MLX 0.32+ and redesign the Torch-MLX tensor bridge (#32984)
Co-authored-by: Alex Nails <alex.nails@radixark.ai>
2026-08-21 18:51:42 -07:00
Baizhou Zhang 3b5909de0e [DeepSeek V4] Add W4A4 MegaMoE server flag (#35918) 2026-08-21 18:44:18 -07:00
DarkSharpnessandClaude Opus 5 7fd5454335 [DSA] Route the ragged prefill top-k to the v2 kernel (#35175)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-21 16:59:41 -07:00
Baizhou Zhang 60ff1e33a5 [DeepSeek V4] Default FP4 checkpoints to FlashInfer MXFP4 MoE (#35919) 2026-08-21 16:48:58 -07:00
Rain Jiang 7d7ab4b5c6 Rainj me/rust server refactor2 (#35239) 2026-08-21 16:37:02 -07:00
Yanbin Jiang 7d893255c3 [Spec][LoRA] Support multi-adapter LoRA with EAGLE/NEXTN/DFLASH/DSPARK speculative decoding (#34337) 2026-08-21 14:21:53 -07:00
Connor Carpenter c3735625de fix(grpc): derive choice count before normalization (#35778)
Signed-off-by: Connor Carpenter <connorc@nvidia.com>
2026-08-21 11:29:52 -07:00
Mohammad Miadh AngkadandMohammad Angkad 61c2da42bb [Fix] Pass Anthropic thinking history as reasoning_content for custom chat encoders (#35480)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-08-22 02:22:11 +08:00
Xiaoyu Zhang 39d4d65a51 [diffusion] Accelerate SANA-Video linear attention in quality=high (#35728) 2026-08-21 18:05:43 +08:00
jasonjk-park 0db2c53dec Fix overlap prebuilt row reuse race (#35748) 2026-08-21 02:00:13 -07:00
Liangsheng Yin 896acc8860 [Fix] Clear full-to-SWA mapping with index_fill_ to avoid a blocking H2D copy (#35773) 2026-08-21 01:23:26 -07:00
Shuwen Wang 8ff9c2b227 [mem_cache][9/N] refactor: move DSAIndexerPoolHost to pool_host.dsa (#35306) 2026-08-21 15:59:15 +08:00
8a123cbd0e [Refactor] New EPD (#30398)
Co-authored-by: Yuang Chen <1131578721@qq.com>
Co-authored-by: Yuang Chen <cya539102@antgroup.com>
Co-authored-by: ZhengWG <zwg0606@gmail.com>
2026-08-21 15:22:48 +08:00
a688682f4b [AMD][CI] Fix ROCm 7.0's dead apt index fail the MORI dependency install (#35764)
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: quitenode <quitenode@users.noreply.github.com>
2026-08-20 22:13:09 -07:00
Ke Bao 73a2c117c6 Support mxfp8 KV cache in PD transfer (#35718) 2026-08-21 13:05:06 +08:00
bda9952377 [AMD] DeepSeek-V4 MI355X: eliminate bpreshuffle fp8-scale copies at producer sites (MoE down, MLA o_proj bmm) (#33166)
Co-authored-by: kk <43161300+kkHuang-amd@users.noreply.github.com>
Co-authored-by: Thomas Wang <thomawan@amd.com>
2026-08-20 21:46:23 -07:00
Zhangheng 44806dc507 Using unified radix tree by default for all case (#35081) 2026-08-21 10:45:46 +08:00
Xiaoyu Zhang 7e80e889a2 [diffusion] Fuse LTX-2.5 decoder 3D RoPE (#35698) 2026-08-21 10:13:09 +08:00
ishandhananiandShangming Cai 978244d671 [P/D disagg] Decode-side radix cache for SWA hybrid models (unified radix tree) (#27770)
Co-authored-by: Shangming Cai <csmthu@gmail.com>
2026-08-21 09:25:06 +08:00
Nan Jiang f825d72936 [Sampling] Restore finite top-k requirement for sampling masks (#35205) 2026-08-20 16:55:25 -07:00
ethcheandEthan Che 67f6ad61d9 fix(kernel) Fix Helion small-token prefill bug (#35197)
Co-authored-by: Ethan Che <eche@meta.com>
2026-08-20 16:41:59 -07:00
Shenxiu LiuandQiaolin Yu 779e593bd1 Fix _GenerationStreamAccumulator logprob_end off-by-one under retract (#26510)
Co-authored-by: Qiaolin Yu <liin1211@outlook.com>
2026-08-20 16:03:13 -07:00
Jiajun Li a4ef828207 fix(openai): avoid duplicate routed expert in response when return_meta_info = True (#35323) 2026-08-20 15:21:58 -07:00
Liangsheng Yin 0149f56e84 [CI] Gate /rerun-test on commenter trust and remove /rerun-stage (#35750) 2026-08-20 15:05:52 -07:00
ishandhananiandAlex Nails 0f744b6848 feat: make mm_inputs msgpack-native (#29656)
Co-authored-by: Alex Nails <alex.nails@radixark.ai>
2026-08-20 14:30:07 -07:00
eac91ac362 [Fix] Land the decode mamba checkpoint depth on the tree page under DCP (#35412)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Ke Bao <ispobaoke@gmail.com>
2026-08-20 12:15:42 -07:00
Chao Shi 2ef0fe4669 TP/PP Consensus checker (#34406) 2026-08-21 01:36:03 +08:00
Ke Bao ba97cc6397 Skip empty linear-attention state buffers in PD transfer (#35689) 2026-08-21 01:00:50 +08:00
Shuwen Wang 9b249a25a1 test: switch the Inkling-Small NVFP4 deterministic suite to DSPARK (#35293) 2026-08-20 21:54:52 +08:00
Mohammad Miadh Angkad a4ffb996db [Fix] Keep deterministic GDN prefill on Triton (#35632) 2026-08-20 19:38:53 +08:00