 Trevor Morris
|
5da265de30
|
[NVIDIA] Fix FP8 gemm performance with fp16 models (MInimax-M2.5) (#22300)
|
2026-06-07 02:45:00 +00:00 |
|
|
Xiaoyu Zhang
|
2c3e84affe
|
[Diffusion] Enable Cosmos3 denoising profiling (#27439)
|
2026-06-07 10:32:28 +08:00 |
|
|
Yueming Yuan
|
4c8a022f38
|
Fix DeepSeek V4 DP reduce scatter when use attention DP + MoE TP (#27191)
|
2026-06-06 18:24:33 -07:00 |
|
|
Liangsheng Yin
|
5160f7914e
|
Fix MLA EAGLE draft CUDA-graph kv_indices under-allocation for topk > 1 (#27460)
|
2026-06-06 16:28:34 -07:00 |
|
|
Liangsheng Yin
|
032c9efb46
|
Enable async-assert invariant probes by default in CI (#27461)
|
2026-06-06 16:23:21 -07:00 |
|
|
Qiaolin Yu
|
4b0f629082
|
[perf] reduce radix cache match overhead by changing the match algorithm (#27364)
|
2026-06-06 15:40:28 -07:00 |
|
|
Liangsheng Yin
|
1c7acba579
|
[spec] Consolidate the per-decode KV alloc reserve into one helper (#27458)
|
2026-06-06 14:58:50 -07:00 |
|
|
Cheng WanandClaude Opus 4.8
|
9097647090
|
Route the eager forward path through the CUDA graph input-buffer registry (#27407)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-06-06 14:35:53 -07:00 |
|
|
Liangsheng Yin
|
84ca0ffb8c
|
Spec v2 tree drafting (topk>1) with page_size>1 (#26972)
|
2026-06-06 12:00:27 -07:00 |
|
|
|
88a7b0fd30
|
Classify malformed-multimodal rejects as invalid_request (#27451)
Co-authored-by: cctry <cctry@meta.com>
Co-authored-by: cctry <cctry@fb.com>
|
2026-06-06 10:19:22 -07:00 |
|
|
|
bd7fea0740
|
[diffusion] Fix LingBot-World crash on camera control with ulysses>1 (#27437)
Co-authored-by: BBuf <xiaoyu.zhang@radixark.net>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-06-06 22:02:29 +08:00 |
|
|
Xiaoyu Zhang
|
7c6f9542c7
|
[Diffusion] Avoid GPU syncs in UniPC scheduler (#27440)
|
2026-06-06 22:01:41 +08:00 |
|
|
|
4e14b50c48
|
[NPU]Support torch_npu profiler patch API drift (#26356)
Co-authored-by: leland17 <lileliao@foxmail.com>
Co-authored-by: OmX <omx@oh-my-codex.dev>
Co-authored-by: ronnie_zheng <zl19940307@163.com>
|
2026-06-06 16:27:51 +03:00 |
|
|
shuwenn
|
280280ace9
|
[SPEC] fix: import copy module for eagle sampling info clone (#27390)
|
2026-06-06 12:12:46 +00:00 |
|
|
fzyzcjy
|
99cf0a4399
|
Fix flaky test_self_e2e_pd_perturb (#27426)
|
2026-06-06 19:31:08 +08:00 |
|
|
|
42fe025280
|
[HiCache] Fix the compatibility between PP and HiCache (L2). (#27285)
Co-authored-by: ybyang <ybyang7@iflytek.com>
Co-authored-by: hzh0425 <hzh0425@apache.org>
Co-authored-by: shangmingc <csmthu@gmail.com>
Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com>
|
2026-06-06 16:57:23 +08:00 |
|
|
Liangsheng Yin
|
aa5213abb1
|
[debug] Register #27338 EAGLE draft kv_indices revert in pr_fix_toggle (#27428)
|
2026-06-06 00:30:13 -07:00 |
|
|
Liangsheng Yin
|
26b9053dcc
|
[Spec] Fix fa3 EAGLE draft-decode expand page_table scatter OOB for topk>1 + page_size>1 (#27360)
|
2026-06-06 00:24:34 -07:00 |
|
|
EduardDurech
|
e9dbbd19e9
|
[model] Apertus Tool/Function and Reasoning parser (#25100)
|
2026-06-06 00:04:31 -07:00 |
|
|
Qiaolin Yu
|
8c47b7678a
|
[attn backend] clean legacy init_mha_chunk_metadata in trtllm_mla backend (#27403)
|
2026-06-05 23:30:21 -07:00 |
|
|
Xiaoyu ZhangandBBuf
|
f57f8a8afd
|
Optimize Gemma4 H200 MoE and extend attention (#26588)
Co-authored-by: BBuf <xiaoyu.zhang@radixark.net>
|
2026-06-06 14:14:25 +08:00 |
|
|
|
e513c13e2e
|
Optimize ngram decode token table update (#24756)
Co-authored-by: Codex <codex@example.com>
Co-authored-by: BBuf <xiaoyu.zhang@radixark.net>
|
2026-06-06 14:13:45 +08:00 |
|
|
zijiexiaandClaude Opus 4.8
|
9da88e32e0
|
[Cohere2Moe] Enable flashinfer_trtllm NVFP4 fused-MoE via SigmoidRenorm routing (#27401)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-06-05 22:49:20 -07:00 |
|
|
Brayden ZhongandBrayden Zhong
|
38ae22e08c
|
Nemotron perf changes (#26733)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
|
2026-06-05 22:31:46 -07:00 |
|
|
Yuxuan Zhang
|
393d0e169e
|
[Bugfix] Restore overridden HF config fields and support index_skip_topk_offset for DSA topk sharing (#27114)
|
2026-06-06 13:26:04 +08:00 |
|
|
kkandwunhuang
|
aa55657e9e
|
[AMD][WA] force to use gate_mode interleaved to fix tp2/tp4/tp8 acc issue (#27201)
Co-authored-by: wunhuang <wunhuang@amd.com>
|
2026-06-05 20:18:11 -07:00 |
|
|
Mick
|
bf66b7b6da
|
[diffusion] model: support Ideogram4 NVFP4 (#27379)
|
2026-06-06 11:14:28 +08:00 |
|
|
Mick
|
e8668508d1
|
[diffusion] optimize: optimize LingBot realtime sp cache path (#27383)
|
2026-06-06 09:37:29 +08:00 |
|
|
Liangsheng Yin
|
58a05d3dd2
|
[CI] Isolate CUDA coredump dir per run to fix tracker mis-attribution (#27344)
|
2026-06-05 21:31:22 -04:00 |
|
|
Xinyi SongandHaiShaw
|
3030119ef7
|
[bugfix][AMD] AttributeError and warp mask bugs in DeepSeek V4 FP4 indexer (#27152)
Co-authored-by: HaiShaw <hixiao@gmail.com>
|
2026-06-05 18:26:38 -07:00 |
|
|
Chi McIsaac
|
25d8f431d1
|
[diffusion] optimize: cosmos3 fused qknorm rope (#27096)
|
2026-06-06 09:15:42 +08:00 |
|
|
fzyzcjy
|
bf4f2ccc78
|
Add scripted-runtime unit, core integration, and chunked-prefill tests (#27413)
|
2026-06-06 09:08:35 +08:00 |
|
|
fzyzcjy
|
5a82db85f0
|
Add scripted-runtime KV-pool and lock-ref exhauster primitives (#27412)
|
2026-06-06 09:07:40 +08:00 |
|
|
fzyzcjy
|
dd176387c6
|
Add scripted-runtime harness core and wire scheduler/IPC hooks (#27411)
|
2026-06-06 09:07:01 +08:00 |
|
|
fzyzcjy
|
21201ef718
|
Add kv_canary PP self-test fixture and SWA divergence coverage (#27410)
|
2026-06-06 09:06:19 +08:00 |
|
|
cctry
|
b3e4c204fd
|
Don't write crash dump on graceful exit (#27405)
|
2026-06-05 17:06:39 -07:00 |
|
|
DevashishLal-CBandDevashish Lal
|
6a3316dd1e
|
[plugin] default device detection fixes for OOT platform plugins (#25337)
Signed-off-by: Devashish Lal <devcode@fb.com>
Co-authored-by: Devashish Lal <devcode@fb.com>
|
2026-06-06 07:55:50 +08:00 |
|
|
ThanhhaoandHao Phan
|
2e7523ddbe
|
fix(spec-dec): treat num_nextn_predict_layers=0 the same as absent for EAGLE3 drafts (#26726)
Co-authored-by: Hao Phan <htphan@nvidia.com>
|
2026-06-05 16:08:07 -07:00 |
|
|
xutizhou
|
29591594f5
|
Support Waterfill with dynamic EPLB (#27150)
|
2026-06-05 16:01:16 -07:00 |
|
|
|
6b180959a8
|
[SPEC][5/N] feat: batchsize-aware support for adaptive speculative_num_steps (#24055)
Co-authored-by: 坤钧 <maoyuhan.myh@antgroup.co>
Co-authored-by: alphabetc1 <alphabetc1@users.noreply.github.com>
Co-authored-by: EanWang211123 <wangyiheng@sangfor.com.cn>
Co-authored-by: shuwenn <47200617+alphabetc1@users.noreply.github.com>
Co-authored-by: shuwenn <2508695655@qq.com>
|
2026-06-05 15:43:02 -07:00 |
|
|
|
c9f582a272
|
[LoRA] Experimental fast LoRA path with experimental_sgl_trtllm MoE backend for FP8 and NVFP4 models (#27329)
Co-authored-by: fzyzcjy <ch271828n@outlook.com>
Co-authored-by: Chunan Zeng <zcnrex@gmail.com>
Co-authored-by: Ethan (Yusheng) Su <yushengsu.thu@gmail.com>
|
2026-06-05 14:45:59 -07:00 |
|
|
Brayden ZhongandBrayden Zhong
|
d381ec7997
|
[CI] Fix Nemotron nightly mixed precision checkpoints test (#27284)
Co-authored-by: Brayden Zhong <brayden.zhong@radixark.ai>
|
2026-06-05 13:51:26 -07:00 |
|
|
Brayden ZhongandBrayden Zhong
|
3b62286fca
|
Reland "Support NextN = 2/4 in DSV32" (#27166)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
|
2026-06-05 13:43:28 -07:00 |
|
|
Liangsheng Yin
|
2c2a4f243a
|
[Bug] Fix EAGLE draft CUDA-graph kv_indices under-allocation for topk > 1 (#27338)
|
2026-06-05 16:22:04 -04:00 |
|
|
Shangming Cai
|
57909f731b
|
[PD] Fix KV cache corruption on abort by notifying ongoing prefill (#27372)
Signed-off-by: Shangming Cai <csmthu@gmail.com>
|
2026-06-06 00:56:13 +08:00 |
|
|
xlyandMick
|
d01cf27b7d
|
[diffusion] model: support Ideogram 4 FP8 (#27279)
Co-authored-by: Mick <mickjagger19@icloud.com>
|
2026-06-05 23:54:48 +08:00 |
|
|
Michael_miaoande01448
|
e7f94d0d40
|
[Bug Fix] Fix activation.cuh JIT compilation failure on CUDA 13 due to template type/value mismatch (#26444)
Co-authored-by: e01448 <jwmao@birentech.com>
|
2026-06-05 22:59:24 +08:00 |
|
|
Aurick Qiao
|
c06802dc16
|
Fix customized_info incremental streaming (#27205)
|
2026-06-05 21:55:01 +08:00 |
|
|
Zhangheng
|
faa6286946
|
[BugFix]: Fix HiMamba HiCache prefetch hang after L3 sidecar transfer (#27366)
|
2026-06-05 20:37:40 +08:00 |
|
|
XiaoTianandgongxiaotian
|
e1955bf57a
|
fix(pd): clear stale bootstrap_room when freeing metadata buffer slot (#27374)
Co-authored-by: gongxiaotian <gongxiaotian@didiglobal.com>
|
2026-06-05 19:46:35 +08:00 |
|