Skip to content

Pull requests: NVIDIA/cudnn-frontend

New pull request New
51 Open 460 Closed
51 Open 460 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

dsa(indexer_backward): optimize SM100 gradient kernels
#730 opened Aug 25, 2026 by jiayus-nvidia Contributor Loading…
3
Map CUDNN_KNOB_TYPE_TILE_CGA so knob queries and explicit plans round-trip
#729 opened Aug 25, 2026 by brandonfzhang Collaborator Loading…
1
python: fix -Werror unused-parameter build break in init_gnn_submodule (pre-9.26 headers) cat-bugfix mod-frontend cuDNN frontend APIs, operation graph construction, plans, and user-facing wrappers. orig-nv-eng Reported or requested by NVIDIA engineering.
#728 opened Aug 25, 2026 by brandonfzhang Collaborator Loading…
1
Fix -Werror=unused-parameter build failure in python/gnn.cpp against cudnn < 9.26 headers
#726 opened Aug 25, 2026 by zkyue Contributor Loading…
2 of 3 tasks
1
Restore pre-1.27 module paths as deprecated aliases; clearer lazy-import errors
#724 opened Aug 24, 2026 by Anerudhan Collaborator • Draft
1
Change RoPE computation to bf16 precision to match MCore's triton implementation
#723 opened Aug 24, 2026 by ghadiaravi13 • Draft
3 tasks
9
Add safe beta guard feature for GDN-2 cat-feature Requests for new functionality, APIs, examples, or behavior improvements. mod-frost orig-nv-eng Reported or requested by NVIDIA engineering.
#722 opened Aug 24, 2026 by jhjpark Collaborator Loading…
3 tasks done
5
frost(sdpa): run the KV split the heuristic chose, on the true cluste… cat-perf-bug Performance regressions or cases where behavior is correct but too slow. mod-frost orig-nv-eng Reported or requested by NVIDIA engineering.
#720 opened Aug 24, 2026 by yanzhuo607 Collaborator Loading…
3 tasks done
5
Add SM120 Matmul Support
#719 opened Aug 24, 2026 by yihuawei Loading…
3 tasks done
3
Thd lpt remap cat-feature Requests for new functionality, APIs, examples, or behavior improvements. mod-frost orig-nv-eng Reported or requested by NVIDIA engineering.
#717 opened Aug 24, 2026 by yanzhuo607 Collaborator Loading…
3 tasks done
11
frost(sdpa): SM80 workspace carving + strided stats — no per-execute allocation on the engine paths (issue #514) cat-enhancements mod-cutedsl CuTeDSL kernels, generated kernels, examples, or related integration work. mod-frost orig-nv-eng Reported or requested by NVIDIA engineering.
#716 opened Aug 24, 2026 by egilliam-nv Collaborator Loading…
4 tasks done
1
19
add det 2k and dbias support for sm120 sdpa bwd cat-feature Requests for new functionality, APIs, examples, or behavior improvements. mod-frost orig-nv-eng Reported or requested by NVIDIA engineering.
#707 opened Aug 24, 2026 by Adnios Collaborator Loading…
3 tasks done
Frontend 1.29.0
30
frost(sdpa): derive THD token capacity from the view's element span (fixes #613) cat-bug Reports of incorrect behavior, crashes, regressions, or unexpected results. mod-cutedsl CuTeDSL kernels, generated kernels, examples, or related integration work. mod-frost orig-nv-eng Reported or requested by NVIDIA engineering.
#706 opened Aug 23, 2026 by vedaanta Collaborator Loading… Frontend 1.29.0
1
4
Add public GELU-MLP and a ModelOpt-anchored Qwen-Image NVFP4 proxy cat-feature Requests for new functionality, APIs, examples, or behavior improvements. mod-frontend cuDNN frontend APIs, operation graph construction, plans, and user-facing wrappers. mod-infra Infrastructure, CI/CD, build systems, packaging, releases, or repo maintenance. orig-nv-eng Reported or requested by NVIDIA engineering.
#695 opened Aug 21, 2026 by YangXu1990uiuc Collaborator Loading…
3 tasks done
Frontend 1.29.0
5
GGEMM+GLU+RHT+quant kernel now outputs column-wise RHT in ragged tensor layout
#693 opened Aug 21, 2026 by timmoon10 Member Loading…
1 of 3 tasks
3
Improve performance of SM100 DSA backward kernel cat-enhancements mod-cutedsl CuTeDSL kernels, generated kernels, examples, or related integration work. orig-external Reported or requested by an external user, customer, or community contributor.
#684 opened Aug 20, 2026 by Butterfingrz Loading…
2 of 3 tasks
Frontend 1.28.0
@Butterfingrz
7
benchmark: add block_sparse_attention (BSA fwd+bwd vs FA4)
#674 opened Aug 19, 2026 by vedaanta Collaborator Loading… Frontend 1.29.0
4
frost(sdpa): port #585 LPT schedulers to the SM107 fp8 sibling; defaults must obey declared knob domains cat-bug Reports of incorrect behavior, crashes, regressions, or unexpected results. mod-cutedsl CuTeDSL kernels, generated kernels, examples, or related integration work. mod-frost orig-nv-eng Reported or requested by NVIDIA engineering.
#656 opened Aug 19, 2026 by vedaanta Collaborator Loading… Frontend 1.29.0
1
2
test(mhas_v2): NaN-poison ragged capacity tails so capacity-vs-live-token bugs fail deterministically (#624)
#646 opened Aug 18, 2026 by vedaanta Collaborator Loading… Frontend 1.29.0
7
dsa(indexer_backward): opt-in SM100 sparse backward v2 — 1.16-1.92x faster (fp32-accurate d_index_k at no extra cost) cat-enhancements mod-cutedsl CuTeDSL kernels, generated kernels, examples, or related integration work. op: DSA DSA related orig-external Reported or requested by an external user, customer, or community contributor.
#640 opened Aug 18, 2026 by zkyue Contributor Loading… Frontend 1.28.0
@zkyue
11
test(python): stop segfaults and CUDA IMAs from poisoning the rest of the run cat-ci CI failures, test flakiness, workflow breakage, or automation issues. mod-infra Infrastructure, CI/CD, build systems, packaging, releases, or repo maintenance. orig-nv-eng Reported or requested by NVIDIA engineering.
#639 opened Aug 17, 2026 by hwanseoc Member • Draft
4
sdpa: throw cudnnGraphNotSupportedException when no implementation supports the attributes
#633 opened Aug 17, 2026 by vedaanta Collaborator Loading… Frontend 1.29.0
1
test: directed SDPA bwd test for rows with very negative LSE
#628 opened Aug 17, 2026 by vedaanta Collaborator Loading… Frontend 1.29.0
4
frost(sdpa): order every execute-path tensor prep on the launch stream (Rule 5) cat-bugfix mod-cutedsl CuTeDSL kernels, generated kernels, examples, or related integration work. mod-frost orig-nv-eng Reported or requested by NVIDIA engineering.
#614 opened Aug 16, 2026 by vedaanta Collaborator Loading…
3 tasks done
Frontend 1.29.0
7
NSA compression: suppress aliased O1 store for static short queries
#599 opened Aug 14, 2026 by mgoldfarb-nvidia • Draft
2 of 3 tasks
1
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.