 Feng Yao
|
e6c15f76f3
|
[optimize] fix swa eviction boundary for unfinished inserts (#29350)
|
2026-06-30 00:19:15 +08:00 |
|
|
Jyothirmai KottuandXinyuan Tong
|
473a278dd1
|
model: support nvidia/LocateAnything-3B (#28958)
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
|
2026-06-30 00:16:42 +08:00 |
|
|
McZyWu
|
bb7d3440b5
|
bugfix revise interface get cpu copy for npu mem pool to align with gpu (#29146)
|
2026-06-29 19:30:14 +08:00 |
|
|
danielafrimiandDaniel Afrimi
|
a2b5ce2ed1
|
Add stochastic rounding for FP16 Mamba SSM cache (#26929)
Signed-off-by: Daniel Afrimi <dafrimi@login-lyris01.lyris.clusters.nvidia.com>
Co-authored-by: Daniel Afrimi <dafrimi@login-lyris01.lyris.clusters.nvidia.com>
|
2026-06-29 01:47:09 -07:00 |
|
|
iridiumineandiridiumine
|
d5133e925b
|
[NPU][Bugfix] Add scoring_func for mimo_v2 (#29493)
Co-authored-by: iridiumine <iridiumine@users.noreply.github.com>
|
2026-06-29 16:34:54 +08:00 |
|
|
bef0rewind
|
3b1b512a9a
|
Fix disaggregation receiver ZMQ cleanup (#29570)
|
2026-06-29 16:22:29 +08:00 |
|
|
SSSunzt
|
91cf159696
|
[PP] bugfix: include CP size in PP rank offset (#29571)
|
2026-06-29 16:01:41 +08:00 |
|
|
Liangsheng Yin
|
c0d45cda29
|
[Spec] Add DFLASH basic sanity CI test (#29338)
|
2026-06-28 23:45:05 -07:00 |
|
|
AndyLi429
|
62d7929b3a
|
[NPU][Bugfix] Accept in_capture in Ascend replay metadata (#29598)
|
2026-06-29 14:37:45 +08:00 |
|
|
Yueming Yuan
|
cd91dd0757
|
fix test_weight_checker_comparator assertion and ue8m0 scale unpack (#29623)
|
2026-06-28 23:36:37 -07:00 |
|
|
silencejade
|
f85cc94d82
|
[NPU] Qwen3-VL-30B use split_qkv_rmsnorm_rope for extend (#29505)
|
2026-06-29 14:35:19 +08:00 |
|
|
Lianmin Zheng
|
bb74ed4a8d
|
Replace hasattr with isinstance in SHM feature helpers (#29549)
|
2026-06-28 21:31:28 -07:00 |
|
|
Lianmin Zheng
|
f76e707f59
|
Clean up follow-ups for eagle hidden dim clean up (#29546)
|
2026-06-28 21:30:53 -07:00 |
|
|
Peng Xingchen
|
06fd2efedd
|
[NPU][Bugfix] Fix a ModelSlim loading failure (#29029)
|
2026-06-29 09:53:01 +08:00 |
|
|
Liangsheng Yin
|
be17475a1b
|
[Spec] Publish DFLASH verify read-done event for fine-grained WAR barrier (#29541)
|
2026-06-28 18:51:38 -07:00 |
|
|
Yueming Yuan
|
e1ca92a7fd
|
[weight checker] refactor: add precision branch; allow ULP quant err; used chunked compare (#28974)
|
2026-06-28 18:44:05 -07:00 |
|
|
Liangsheng Yin
|
909123ddb8
|
[misc] Use --cuda-graph-max-bs-decode in tests, examples, and docs (#29591)
|
2026-06-28 18:38:28 -07:00 |
|
|
Ma Mingfei
|
3217410cf6
|
[CPU] enable fused_sigmoid_mul on CPU device (#29378)
|
2026-06-29 09:38:04 +08:00 |
|
|
Polisetty V R K Jyothendra Varma
|
d5abafcc1c
|
[Intel GPU] add pytorch profiling support for XPU in bench offline throughput and enhance num steps (#28308)
Signed-off-by: P V R K Jyothendra Varma <polisettyvarma@gmail.com>
|
2026-06-29 09:10:15 +08:00 |
|
|
Liangsheng Yin
|
abaee4664e
|
[dflash] fa3/fa4: device-side page table; drop seq_lens_cpu D2H sync (#29343)
|
2026-06-28 18:06:33 -07:00 |
|
|
Chao Shi
|
bd2a5db987
|
[HiCache] Detect for double-free in HostKVCache (#29310)
|
2026-06-29 09:02:21 +08:00 |
|
|
Brayden ZhongandBrayden Zhong
|
b9b860652e
|
Fix DSA indexer fusion bug causing excessive memory consumption. (#29576)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
|
2026-06-28 14:11:07 -07:00 |
|
|
Aurick Qiao
|
ad30a9958e
|
Fix dummy weight init for tensor subclasses (#29229)
|
2026-06-29 01:17:00 +08:00 |
|
|
Yinghai Lu
|
c5b9388721
|
[scheduler] Add scheduler metrics reporter init hook (#29535)
|
2026-06-28 09:59:34 -07:00 |
|
|
ishandhanani
|
aaa31eb0a1
|
feat: first-class session identity in SGLang (#29436)
|
2026-06-28 07:16:38 -07:00 |
|
|
Lianmin Zheng
|
828411e6f1
|
Fix FlashInfer A2A dispatcher during CUDA graph capture (#29461)
|
2026-06-28 02:21:26 -07:00 |
|
|
Mick
|
4cb6d81bda
|
[diffusion] CI: make consistency GT probe robust to transient CDN failures (#29545)
|
2026-06-28 17:13:53 +08:00 |
|
|
Liangsheng Yin
|
6582fc1e5d
|
dflash: drop verify_done barrier; rely on scheduler WAR fallback (#29556)
|
2026-06-28 01:47:17 -07:00 |
|
|
Liangsheng Yin
|
593f5ba68f
|
[Spec] Replace shared-infra dflash special-cases with capabilities (WAR barrier + seq_lens_cpu) (#29232)
|
2026-06-28 00:02:32 -07:00 |
|
|
Mick
|
643e1cc779
|
fix: fix prefill-aware SWA floor tracking (#29520)
|
2026-06-28 14:18:28 +08:00 |
|
|
Xinyuan Tong
|
ddc389cf09
|
[minimax-m3] Split 3/4: disagg K-only index-K transfer (#28714)
|
2026-06-28 13:54:42 +08:00 |
|
|
Lianmin Zheng
|
6eedc8f376
|
Fix EAGLE draft hidden dim extraction and centralize spec helpers (#29464)
|
2026-06-27 21:48:26 -07:00 |
|
|
Lianmin ZhengandYinghai Lu
|
5747ed3b19
|
Fix DP-attention SHM feature finalization race (#29543)
Co-authored-by: Yinghai Lu <yinghai@meta.com>
|
2026-06-27 21:36:58 -07:00 |
|
|
Mick
|
4a76699dfc
|
[diffusion] fix: fix --warmup silently downgrading server-based warmup to request mode (#29514)
|
2026-06-28 11:46:07 +08:00 |
|
|
Lianmin Zheng
|
e6cbc8f5fe
|
Fix SWA cache loc slicing for all attention backends (#29460)
|
2026-06-27 20:37:58 -07:00 |
|
|
Liangsheng Yin
|
4e6ce8e4ab
|
[Spec] Capture DFLASH draft greedy sampling inside the draft decode cuda graph (#29395)
|
2026-06-27 19:34:26 -07:00 |
|
|
Khoa PhamandCursor
|
da802ddcaf
|
(perf): Shard Kimi-K2.5 Eagle3 draft fc + symm-mem AG (#29223)
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-06-27 17:40:32 -07:00 |
|
|
|
073de15053
|
Fuse the DSA (V3.2, GLM-5.x) indexer Q/K paths into single kernels (#27705)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
Co-authored-by: Kaixi <kaiximatteoc@nvidia.com>
|
2026-06-27 14:29:56 -07:00 |
|
|
Brayden ZhongandBrayden Zhong
|
e4253b39e2
|
Support JIT fused A GEMM (MLA down projection) and support GLM-5 hidden size, SM120 (#27397)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
|
2026-06-27 13:32:06 -07:00 |
|
|
Xinyuan Tongandhzh0425
|
592f6c849b
|
[minimax-m3] Split 2/4: mem-cache / HiCache / sparse KV pool (#28713)
Co-authored-by: hzh0425 <hzh0425@apache.org>
|
2026-06-28 00:19:38 +08:00 |
|
|
Aditya KamatandMick
|
1589603114
|
model: support baidu unlimited-ocr (#29186)
Co-authored-by: Mick <mickjagger19@icloud.com>
|
2026-06-27 23:36:19 +08:00 |
|
|
|
b030b1a5f3
|
hisparse: support NIXL DRAM KV destinations for HiSparse (#27563)
Co-authored-by: Zhangheng <hzh0425@apache.org>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
|
2026-06-27 22:32:29 +08:00 |
|
|
|
c1b5c7e499
|
Fix DeepSeek V4 PP HiCache SWA allocation and layer mapping (#29106)
Co-authored-by: hjzhang <zhanghjzzz@qq.com>
Co-authored-by: hzh0425 <hzh0425@apache.org>
|
2026-06-27 22:19:14 +08:00 |
|
|
jonah-bermanandXinyuan Tong
|
2f34dbe372
|
Add native Exa-backed web_search support (#29342)
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
|
2026-06-27 14:41:09 +01:00 |
|
|
Mick
|
3306233961
|
[diffusion] optimize: optimize LTX2.3 CFG path (#28624)
|
2026-06-27 19:23:14 +08:00 |
|
|
Mick
|
91f9e7372d
|
[diffusion] CI: refactor CI (#28762)
|
2026-06-27 19:22:27 +08:00 |
|
|
|
9214b9338f
|
[DSA] Enable draft-extend CUDA graph for DeepSeek Sparse Attention (#29413)
Co-authored-by: kpham-sgl <kpham-sgl@users.noreply.github.com>
Co-authored-by: Jackey Hua <107608053+zhendonghua@users.noreply.github.com>
|
2026-06-26 23:53:46 -07:00 |
|
|
Raiden MakotoandRaiden-Makoto
|
81d3c3ce77
|
[AMD] [GLM5] Guard cuda_runtime.h for ROCm in fused_metadata_copy (#29373)
Co-authored-by: Raiden-Makoto <Raiden-Makoto@users.noreply.github.com>
|
2026-06-26 23:29:19 -07:00 |
|
|
Xiaoyu Zhang
|
c36f166364
|
[skill] Remove outdated llm-serving-auto-benchmark skill (#29487)
|
2026-06-27 14:19:11 +08:00 |
|
|
Chengze Fan
|
43435a2f8e
|
[mori] Add a combine-kwargs hook and use_external_inp_buf plumbing (#29097)
|
2026-06-26 22:34:27 -07:00 |
|