Xiaoyu Zhang
|
391e665dab
|
[Perf] Optimize DeepSeek V4.1 Flash Hopper paths and Blackwell prefill selection (#41251)
|
2026-10-03 10:04:48 +08:00 |
|
 
|
8ff02f5820
|
[QSA] Enable breakable prefill CUDA graphs for text-only Qwen3.8 Flash-Next (capture-safe metadata, MTP side-channel padding) (#41729)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Qiaolin Yu <liin1211@outlook.com>
|
2026-10-02 17:57:42 -07:00 |
|
 caihuali95andCheng Wan
|
2a3655fea1
|
[unified-memory] Name the fused KV translate for what it computes (7/7) (#40331)
Co-authored-by: Cheng Wan <cheng.wan@radixark.ai>
|
2026-10-01 17:14:03 -07:00 |
|
 
|
9855e9c6f8
|
[unified-memory] Remove the kernel-page multiplier plumbing (5/7) (#40329)
Co-authored-by: Caihua Li <caihua.li@bytedance.com>
Co-authored-by: Cheng Wan <cheng.wan@radixark.ai>
|
2026-10-01 17:11:25 -07:00 |
|
 
|
cdadb1c79a
|
[unified-memory] Token-major dense views for the unified memory pool (3/7) (#38592)
Co-authored-by: Caihua Li <caihua.li@bytedance.com>
Co-authored-by: Cheng Wan <cheng.wan@radixark.ai>
|
2026-10-01 17:09:38 -07:00 |
|
       
|
f17f7705a5
|
[AMD] [GLM-5.3-Flash] Enable FP8 and MXFP4 serving on gfx950 (#39273)
Co-authored-by: Byron Hsu <byron+per@periodiclabs.ai>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
Co-authored-by: long10024070 <long10024070@users.noreply.github.com>
Co-authored-by: Kevin Mi <45493463+kevin-mii@users.noreply.github.com>
Co-authored-by: Kevin Mi <mikevin920@yahoo.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: sunxxuns <126995791+sunxxuns@users.noreply.github.com>
Co-authored-by: Long Luong <long.luong2+personal@onemount.com>
|
2026-10-01 15:59:44 -07:00 |
|
amd-danli103
|
9c3262d855
|
[AMD][DSV4] feat: enable PD-disagg with fp8 unified_kv on gfx950 (#39166)
|
2026-09-30 23:42:31 -07:00 |
|
Cheng Wan
|
a9c97c9f69
|
[Feature] Add --attn-dp-size and deprecate --enable-dp-attention (#41818)
|
2026-09-30 13:34:18 -07:00 |
|
Cheng Wan
|
986cb8268b
|
[Refactor] Enter draft TP scopes by attention ownership and drop ModelRunner.tp_group (#41817)
|
2026-09-30 13:28:50 -07:00 |
|
Cheng Wan
|
499e86db98
|
[Refactor] Keep only the TP and PP groups on the model runner (#41813)
|
2026-09-30 13:27:31 -07:00 |
|
Cheng Wan
|
01b5f572b7
|
[Refactor] Rename layer boundary protocols, contracts and helpers (#41750)
|
2026-09-29 21:05:48 -07:00 |
|
 
|
84523d6785
|
[Spec] Reuse K3 auxiliary outputs across decode CUDA graph sizes (#40159)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
|
2026-09-29 14:24:51 -07:00 |
|
  
|
7889fbab9a
|
[PD] Keep EAGLE DP graph and token metadata consistent (#32196)
Co-authored-by: weireweire <20922698+weireweire@users.noreply.github.com>
Co-authored-by: Po-Han Huang (NVIDIA) <53919306+nvpohanh@users.noreply.github.com>
Co-authored-by: Khoa Pham <khoa.pham@radixark.ai>
|
2026-09-28 17:15:51 -07:00 |
|
Cheng Wan
|
0e907b755d
|
[Refactor] Split the layer communicator into a package (move only) (#41439)
|
2026-09-27 16:54:41 -07:00 |
|
Cheng Wan
|
427c9e05c1
|
[Refactor] Choose every layer's boundaries from declarations and remove the scatter-mode selection (#41438)
|
2026-09-27 16:54:18 -07:00 |
|
Cheng Wan
|
7a833ad0a2
|
[Refactor] Choose a GQA prefill CP extend's steps from declarations (#41421)
|
2026-09-27 16:48:17 -07:00 |
|
 
|
c10fa03fc4
|
Make sliding-window caching and speculative batch padding extensible (#41325)
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
Co-authored-by: jasonjk-park <jasonjk@fb.com>
|
2026-09-26 11:24:02 -07:00 |
|
Xiaoyu Zhang
|
38ec649048
|
[Refactor] Restore logical kernel groups and test organization (#41243)
|
2026-09-26 12:30:44 +08:00 |
|
Liangsheng Yin
|
f35ec18d8b
|
[Test] Remove more unit tests that mirror implementation or never run in CI (#41297)
|
2026-09-25 19:22:14 -07:00 |
|
 
|
cec70a4708
|
[Fix] Keep the target's DP sync slot in draft scopes (#41062)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
|
2026-09-24 21:48:39 -07:00 |
|
 Shuwen Wangandhnyls2002
|
a2025b8c4d
|
[DSV4] Account for FlashMLA physical KV page padding in memory budgets (#41091)
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
|
2026-09-24 17:14:08 -07:00 |
|
Liangsheng Yin
|
0c578d97fe
|
[DSV4] Size compressed pools from one per-ratio table in DSV4PoolConfigurator (#41049)
|
2026-09-24 15:19:02 -07:00 |
|
Shuwen Wang
|
961404b010
|
[DSV4] Fix TRTLLM uniform FP8 KV memory budgeting (#41090)
|
2026-09-24 13:25:00 -07:00 |
|
 
|
f404db94d4
|
[DP attention] Publish DP buffer sizes from a ForwardBatch (#40858)
Co-authored-by: hanminglu <hanminglu@fb.com>
Co-authored-by: oss-sync bot (pranjalssh) <pranjalssh@users.noreply.github.com>
|
2026-09-24 11:34:19 -07:00 |
|
Yuwei An
|
1417345f5f
|
[Experimental] Preserve speculative decoding during prefill across DP ranks (#40118)
|
2026-09-24 00:01:12 -07:00 |
|
Liangsheng Yin
|
cae4927fbf
|
[DSV4] Budget the ratio-2 pair state pool in DSV4PoolConfigurator (#41048)
|
2026-09-23 23:53:46 -07:00 |
|
Shuwen Wang
|
90663ccb41
|
[DSV4] fix: size the C4 state ring by the page it is addressed by (#40337)
|
2026-09-23 22:05:32 -07:00 |
|
      
|
f4d9d2e670
|
[RL] Add RL weight-update sessions and support updating spec draft runners (#40777)
Co-authored-by: Jiajun Li <guapisolo@gmail.com>
Co-authored-by: Nan Jiang <59716405+nanjiangwill@users.noreply.github.com>
Co-authored-by: maocheng23 <maocheng@berkeley.edu>
Co-authored-by: Byron Hsu <byron+per@periodiclabs.ai>
Co-authored-by: JD-ETH <jaedon.guo@gmail.com>
Co-authored-by: Letian Ruan <ruanlt420@gmail.com>
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
|
2026-09-23 20:04:57 -07:00 |
|
Liangsheng Yin
|
cc6e8b0f25
|
[Fix] Derive per-runner hybrid SWA layer ids on ModelLayerInfo instead of mutating ModelConfig (#40983)
|
2026-09-23 19:52:55 -07:00 |
|
Cheng Wan
|
79fec592a8
|
[Refactor] Read parallel placement in consumers (#40638)
|
2026-09-23 14:57:25 -07:00 |
|
Cheng Wan
|
701cf7e47e
|
[Refactor] Run Nemotron-H DP attention through the standard layer communicator (#40867)
|
2026-09-23 14:40:33 -07:00 |
|
 
|
4bb5611dba
|
[Fix] Give the full prefill CUDA graph replay view the captured bucket's input_ids (#40851)
Co-authored-by: metamergebot <324680979+metamergebot@users.noreply.github.com>
Co-authored-by: fei-xx <135589532+fei-xx@users.noreply.github.com>
|
2026-09-23 11:48:03 -07:00 |
|
Yoray Zack
|
de123f38bb
|
[3/N] elastic-ep: Recapture decode CUDA graphs after scale-up (#33723)
|
2026-09-23 01:51:30 -07:00 |
|
 Mohammad Miadh AngkadandMohammad Angkad
|
7b977ce5dc
|
[Fix] Decide the MoE padded-row bound from the layer scatter mode (#40672)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
|
2026-09-22 16:02:17 -07:00 |
|
 
|
6412ad8c64
|
[AMD] Pack Qwen3.5 GDN input projections on ROCm (#39902)
Co-authored-by: Zijie Chen <300606707+zijiecode@users.noreply.github.com>
Co-authored-by: jacky.cheng <yichiche@amd.com>
|
2026-09-22 00:52:40 -07:00 |
|
Cheng Wan
|
9eda772a21
|
[Test] Handle tied top-k indices in graph-pool logprob regression (#40661)
|
2026-09-21 19:02:43 -07:00 |
|
Cheng Wan
|
acac4dd9d9
|
[Refactor] Clean up parallel runtime comments (#40632)
|
2026-09-21 14:32:22 -07:00 |
|
Cheng Wan
|
970e946e4f
|
Retire the per-runner parallel record (#40343)
|
2026-09-21 12:26:40 -07:00 |
|
Cheng Wan
|
73f071db52
|
Deprecate the parallel getters the context answers, and ratchet them shut (#40342)
|
2026-09-21 12:25:32 -07:00 |
|
Cheng Wan
|
65be3fa71a
|
A runner and the objects it builds freeze the placement they describe (#40341)
|
2026-09-21 12:24:17 -07:00 |
|
cctry
|
7a6191c4b9
|
Preallocate HiCache MHA staging before post-capture KV sizing (#40256)
|
2026-09-21 10:44:29 -07:00 |
|
 
|
d229952e25
|
[Fix] Preserve model runner contracts in prefill CUDA graphs (#35452)
Co-authored-by: Oasis-Git <ayw.sirius19@gmail.com>
Co-authored-by: Ke Bao <ispobaoke@gmail.com>
|
2026-09-20 13:53:14 -07:00 |
|
 amd-danli103andHAI
|
e54009240a
|
[AMD][DSV4] feat: enable DSpark with fp8 unified_kv on gfx950 (#38901)
Co-authored-by: HAI <hixiao@gmail.com>
|
2026-09-20 01:16:39 -07:00 |
|
Qiaolin Yu
|
f4c256354c
|
[kimi k3][pd disagg] support pp prefill + dcp decode with dspark (#40045)
|
2026-09-20 00:15:28 -07:00 |
|
 Yuxuan ZhangandXinyuan Tong
|
9f21fbc34b
|
[GLM-5.3-Flash] Reduce KPool planning synchronization and overlap indexer preparation (#39695)
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
|
2026-09-19 23:51:17 -07:00 |
|
 metamergebotandcctry
|
9e5a62a767
|
[Logprob] Serve input-logprob temporaries from CUDA-graph-pool dead space (#40038)
Co-authored-by: cctry <csycfl@gmail.com>
|
2026-09-19 12:03:52 -07:00 |
|
Cheng Wan
|
3a5f52e144
|
Record a process's placement at publish, not at group build (#40071)
|
2026-09-18 23:52:37 -07:00 |
|
Cheng Wan
|
afe71f4b9e
|
Read process groups through the runtime context (#40068)
|
2026-09-18 17:40:32 -07:00 |
|
 metamergebotandcctry
|
6a9c7001d3
|
[Logprob] Borrow graph-pool memory for input logprob logits construction (#40007)
Co-authored-by: cctry <csycfl@gmail.com>
|
2026-09-18 13:18:01 -07:00 |
|
Jialin Ouyang
|
da2f434951
|
[Spec] Add explicit prefill shared-read capability for plugins (#39502)
|
2026-09-18 13:11:01 -07:00 |
|