 Mick
|
25b6051c70
|
[diffusion] warmup: default to model sampling resolution (declare Z-Image default) (#29519)
|
2026-06-30 10:32:11 +08:00 |
|
|
Ho-Ren (Jack) Chuang
|
bc8b3ab1f5
|
[Kernel] Add SM90 Q8KV8 FP8 Sparse MLA Prefill JIT Kernel with Tests and Benchmark (#25751)
|
2026-06-30 09:00:11 +08:00 |
|
|
Ho-Ren (Jack) Chuang
|
a6bc432fd8
|
[Perf][Kernel] Fuse SiLU+Mul into NVFP4 Expert Quantization for CUTLASS MoE (#18612)
|
2026-06-29 16:51:01 -07:00 |
|
|
eeechoandAliceChenyy
|
f0bf96390b
|
[SM120] Add FlashInfer sparse MLA decode for DSv4-Flash (#27455)
Co-authored-by: AliceChenyy <alicechenyy@users.noreply.github.com>
|
2026-06-29 16:27:16 -07:00 |
|
|
Trevor Morris
|
b8c25bfaa7
|
[NVIDIA] Support flashinfer a2a with flashinfer_trtllm_routed moe (#22394)
|
2026-06-29 16:23:58 -07:00 |
|
|
Khoa PhamandClaude Opus 4.7
|
6bdecb8206
|
[DeepSeek V3] Reland: run routed experts on main stream in dual-stream MoE (#29463)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-06-29 15:05:01 -07:00 |
|
|
Xinyuan Tong
|
45314a9fcb
|
[spec] Fix index_share_for_mtp_iteration being a no-op in EAGLE MTP draft (#29654)
|
2026-06-29 14:52:23 -07:00 |
|
|
Cheng Wanandlch1475369
|
fc96edd297
|
feat(mem_cache): page-major (layer-major within a page) KV/state layout (#29533)
Co-authored-by: lch1475369 <lch1475369@gmail.com>
|
2026-06-29 14:49:54 -07:00 |
|
|
Mohammad Miadh Angkad
|
6c018eb4d1
|
Fix bounded checkpoint prefetching and buffered drop-cache handling (#29156)
|
2026-06-29 21:49:16 +00:00 |
|
|
|
5556631789
|
[Speculative Decoding] Validate vocabulary compatibility in STANDALONE mode (#23838)
Co-authored-by: kpham-sgl <khoa.pham@radixark.ai>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-06-29 14:45:12 -07:00 |
|
|
Brayden Zhong
|
98d0e702c3
|
[GLM-5] Tune the threshold of router GEMM (#29470)
|
2026-06-29 14:19:24 -07:00 |
|
|
cctryandcctry
|
a5c45a12bb
|
CUDA graph executable dedup via cudaGraphExecUpdate (#29625)
Co-authored-by: cctry <cctry@fb.com>
|
2026-06-29 13:56:33 -07:00 |
|
|
|
f480c5f1f9
|
[Spec] Frozen-KV MTP: delay target KV binding to pool init + reset stale draft out_cache_loc (#29616)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: bef0rewind <490285+ronhuafeng@users.noreply.github.com>
Co-authored-by: AlejandroParedesLT <99832715+AlejandroParedesLT@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-06-29 11:57:10 -07:00 |
|
|
Mick
|
b0be644133
|
[diffusion] feat: keep image-model auxiliary components resident under auto memory policy (#29649)
|
2026-06-30 01:25:37 +08:00 |
|
|
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 |
|