 Mohammad Miadh AngkadandMohammad Angkad
|
4c81cd1b09
|
[KDA] Fix missing beta sigmoid in PTX prefill (#40685)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
|
2026-09-21 23:24:38 -07:00 |
|
|
YAMY
|
9b59fc5db5
|
[ModelOpt][PP] Keep BF16 shared experts out of the NVFP4 fusion so TP1 pipeline stages can load (#40628)
|
2026-09-21 21:45:58 -07:00 |
|
|
|
e1daf68304
|
[AMD] [GLM-5.3-Flash Day 0] Honor fused and per-expert names in quark exclude (#39317)
Co-authored-by: Yikai Zhang <ykzhang12@gmail.com>
Co-authored-by: Thomas Wang <thomawan@amd.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 Fable 5.1 <noreply@anthropic.com>
|
2026-09-21 21:26:42 -07:00 |
|
|
|
b44e248682
|
[AMD] [GLM-5.3-Flash Day 0] Enable FP8 and Quark MXFP4 MoE on gfx950 (#38546)
Co-authored-by: Raiden-Makoto <Raiden-Makoto@users.noreply.github.com>
Co-authored-by: Thomas Wang <thomawan@amd.com>
Co-authored-by: andyluo7 <andy.luo@amd.com>
Co-authored-by: Kevin Mi <mikevin920@yahoo.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-21 21:07:37 -07:00 |
|
|
Vedant V JhaveriandCopilot
|
9fdb71732a
|
Avoid materializing GDN QKV tensors during target verification (#33778)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
2026-09-21 17:04:18 -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 |
|
|
Cheng Wan
|
2d0e94e3a3
|
Check the topology identities where the layout is written, and build at the published widths (#40340)
|
2026-09-21 12:22:59 -07:00 |
|
|
skyler-apdx
|
f5f3c38aad
|
[Fix] Preserve YaRN scaling when extending rotary caches (#38786)
|
2026-09-21 14:14:05 +08:00 |
|
|
Liangsheng Yin
|
76a9065bef
|
[Fix] Raise on undelivered embeddings in send_with_url, fix broken tests (#40502)
|
2026-09-20 17:35:27 -07:00 |
|
|
|
42875bcd2a
|
fix(modelopt): dispatch NVFP4 MoE on the cached backend, not the live global (#38932)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Po-Han Huang (NVIDIA) <53919306+nvpohanh@users.noreply.github.com>
|
2026-09-20 19:28:54 -04:00 |
|
|
Harmya Bhatt
|
95521da18d
|
[DeepSeek-V4.1] Bound dense prefill indexer memory (#40217)
|
2026-09-20 14:43:19 -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 |
|
|
Yuxuan ZhangandXinyuan Tong
|
c8eb54c41d
|
Fuse GLM-5.3-Flash KDA projections and prefill metadata (#39688)
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
|
2026-09-19 23:46:33 -07:00 |
|
|
YAMY
|
9cc7da2ab0
|
[MegaMoE] Wire Qwen MoE blocks to DeepGEMM MegaMoE (MXFP4 and NVFP4 experts) (#38080)
|
2026-09-19 16:00:38 -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 |
|
|
|
7b67a96640
|
[DSV4] Chunk the indexer MQA logits by query rows under a free-memory budget (#39095)
Signed-off-by: Shiki Wu <shikiw@nvidia.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: Yuwei An <ayw.sirius19@gmail.com>
|
2026-09-19 11:53:20 -07:00 |
|
|
DarkSharpnessandBBuf
|
d1acbe0746
|
[DSV4.1] Big fused wo_a quant (#39957)
Co-authored-by: BBuf <1182563586@qq.com>
|
2026-09-19 19:46:53 +08:00 |
|
|
Cheng Wan
|
567d5925fe
|
Fix mxfp4 padding test stubbing an accessor the module no longer imports (#40308)
|
2026-09-19 00:43:56 -07:00 |
|
|
Xiaoyu Zhang
|
36aa8479ef
|
[Test] Fix fusion-group mocks after runtime context migration (#40290)
|
2026-09-19 14:45:16 +08:00 |
|
|
Liangsheng Yin
|
d507accadc
|
[Test] Drop dead and strictly-subsumed CI test registrations (#40264)
|
2026-09-18 17:49:13 -07:00 |
|
|
Cheng Wan
|
afe71f4b9e
|
Read process groups through the runtime context (#40068)
|
2026-09-18 17:40:32 -07:00 |
|
|
|
0e5347db82
|
Support MXFP8 and deferred route weighting in DeepEP v2 (#40030)
Co-authored-by: metamergebot <324680979+metamergebot@users.noreply.github.com>
Co-authored-by: Xingyu Liu <38244988+charlotte12l@users.noreply.github.com>
Co-authored-by: pranjalssh <14260275+pranjalssh@users.noreply.github.com>
|
2026-09-18 15:40:38 -07:00 |
|
|
Sam (Kesen Li)
|
d346b214fb
|
feat(kv-cache): support SM100 NVFP4 GenMHA and speculative decoding (#36340)
|
2026-09-18 14:50:46 -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 |
|
|
Lianmin Zhengandraghotham
|
248c202b46
|
Use runtime token widths for Triton speculative verification (#39859)
Co-authored-by: raghotham <853234+raghotham@users.noreply.github.com>
|
2026-09-18 11:07:55 -07:00 |
|
|
|
a6cf05817f
|
dsv4.1: remaining model and runtime integration (#38798)
Co-authored-by: BBuf <1182563586@qq.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Xiaoyu Zhang <xiaoyu.zhang@radixark.ai>
Co-authored-by: Yuwei An <ayw.sirius19@gmail.com>
Co-authored-by: Khoa Pham <khoa.pham@radixark.ai>
Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com>
Co-authored-by: Zhichen Zeng <zczeng@uw.edu>
Co-authored-by: Ke Bao <ispobaoke@gmail.com>
|
2026-09-18 02:55:30 -07:00 |
|
|
Liangsheng Yin
|
1b200ffaaa
|
[Quant] Serve 32-wide-K ue8m0 block-FP8 linears through the FlashInfer MXFP8 GEMMs (#40039)
|
2026-09-18 02:51:12 -07:00 |
|
|
Shu Wang
|
1e8699fda3
|
[NVIDIA][comm] Merge EP+MoE-TP post-experts all-reduces into one _TP reduction (#32963)
|
2026-09-18 01:35:10 -07:00 |
|
|
maithilijoshi20
|
0dad91d50f
|
Fix int4 MoE tuner config filename (#35260)
Signed-off-by: maithilijoshi20 <maithilij2003@gmail.com>
|
2026-09-18 13:56:38 +08:00 |
|
|
|
acfde25d34
|
Carry deferred attention operands and reuse multimodal shared memory (#39870)
Co-authored-by: fei-xx <135589532+fei-xx@users.noreply.github.com>
Co-authored-by: jmswen <jmswen@gmail.com>
|
2026-09-17 01:17:15 -07:00 |
|
|
Xinyuan Tong
|
f0bf652534
|
Add Ling-3.0-flash-VL model support (#38526)
|
2026-09-17 00:19:26 +08:00 |
|
|
ShunkangzandZhangheng
|
e7f7447333
|
[kv-shard 2/4] Sharded pools (#37615)
Co-authored-by: Zhangheng <hzh0425@apache.org>
|
2026-09-16 19:22:23 +08:00 |
|
|
Rahul Vijayaraghavan
|
d4ad368ed9
|
[Intel XPU] Enable fused_moe_triton tuning on XPU and add tuned DeepSeek-OCR-2 configs (#28723)
|
2026-09-16 10:20:22 +08:00 |
|
|
Cheng Wan
|
406c9c71d8
|
[Feature] Support BF16 and batch-invariant inference with DeepEP v2 (#38160)
|
2026-09-15 14:30:50 -07:00 |
|
|
Aurick QiaoandAurick Qiao
|
5dde6e8f02
|
Fix MegaMoE buffer allocation and caching for effective SM budgets (#39223)
Co-authored-by: Aurick Qiao <6137920+aurickq@users.noreply.github.com>
|
2026-09-15 10:24:02 +08:00 |
|
|
Cheng Wan
|
6410800af9
|
[unified-memory] Enable prefill cuda-graph capture (#37418)
|
2026-09-13 19:17:19 -07:00 |
|
|
|
cebca698e2
|
[Qwen3.8] Enable NVIDIA NVFP4 on DGX Spark with file-backed PLE and PDL router fix (#39126)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: rdxa <rdxa@rdxa-int-spark-01.yvb.moe>
Co-authored-by: Yangmin Li <yangminl@nvidia.com>
Co-authored-by: Manrique <nanomlm@gmail.com>
Co-authored-by: yhyang201 <yhyang201@gmail.com>
|
2026-09-13 16:23:41 +08:00 |
|
|
Tuan Nguyen Gia
|
7c195b9151
|
[AMD] Fix Quark load of MiniMax-M3 MXFP4 index_qkv_proj (#37254)
|
2026-09-12 00:50:41 -07:00 |
|
|
Mohammad Miadh AngkadandMohammad Angkad
|
4309c7ce19
|
Fix stale DSV4 indexer metadata names in the TopK v2 dispatch test (#39101)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
|
2026-09-11 08:31:42 -07:00 |
|
|
|
335f6aab27
|
[DSV4] Support raw-index output in TopK v2 (#33672)
Co-authored-by: weireweire <20922698+weireweire@users.noreply.github.com>
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
Co-authored-by: Po-Han Huang (NVIDIA) <53919306+nvpohanh@users.noreply.github.com>
|
2026-09-11 07:17:36 -07:00 |
|
|
ANSHUMAN TRIPATHY
|
3716e496ea
|
Speculative Decoding support for intel_xpu attention backend on XPU target (#30548)
|
2026-09-11 10:25:25 +08:00 |
|
|
Liangsheng Yin
|
41da06adca
|
[Refactor] Generalize DeepSeek V4 compressed pool management (#38954)
|
2026-09-10 17:29:03 -07:00 |
|
|
Liangsheng Yin
|
dc5f59c3a2
|
[Refactor] Clarify DeepSeek V4 metadata names for V4.1 (#38947)
|
2026-09-10 15:42:52 -07:00 |
|
|
|
1b77f498a0
|
[NVIDIA] Support flashinfer Mega Moe (#31470)
Co-authored-by: djns99 <40156487+djns99@users.noreply.github.com>
Co-authored-by: 云挚 <ningyunxiao.nyx@antgroup.com>
Co-authored-by: Yangmin Li <yangminl@nvidia.com>
Co-authored-by: Po-Han Huang (NVIDIA) <53919306+nvpohanh@users.noreply.github.com>
|
2026-09-10 00:22:47 -07:00 |
|
|
Brayden ZhongandBrayden Zhong
|
c0b790cf7f
|
Delete cutlass_mla, non-Marlin GPTQ, AWQ AOT kernel, and Dual Chunk Flash Attention (#32114)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
|
2026-09-10 15:12:01 +08:00 |
|
|
DAI0818andPo-Han Huang
|
03e4c06589
|
Fix Qwen3.5 GDN multi-item scoring (#33922)
Co-authored-by: Po-Han Huang (NVIDIA) <53919306+nvpohanh@users.noreply.github.com>
|
2026-09-09 22:30:39 -07:00 |
|
|
|
fd596a474c
|
[XPU][Fix] Pack device-pointer tables as uint64 to avoid 64-bit address overflow (#35051)
Co-authored-by: roopaksrivastav <roopak.srivastava@intel.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-09-10 10:12:18 +08:00 |
|