Skip to content

Pull requests: NVIDIA/cudnn-frontend

New pull request New
13 Open 167 Closed
13 Open 167 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: add q causal offsets and Rubin SM100F support
#316 opened Jun 17, 2026 by jiayus-nvidia Contributor Loading…
6
fix(sdpa_benchmark): use sampled SM clock + per-arch MMA throughput for SOL%
#314 opened Jun 16, 2026 by brandonfzhang Contributor Loading…
1
fix: IMA on indexer_topk_wrapper
#312 opened Jun 16, 2026 by Hyaloid Loading…
3
Test softmax stats outputs in various permutations
#304 opened Jun 11, 2026 by egilliam-nv Contributor • Draft
4
Add byte boolean frontend data type
#302 opened Jun 10, 2026 by yeliu-oss Loading…
1
fp8 support in unified fprop
#301 opened Jun 10, 2026 by egilliam-nv Contributor • Draft
1
experimental: grouped gemm AOT cat-feature Requests for new functionality, APIs, examples, or behavior improvements. mod-frontend cuDNN frontend APIs, operation graph construction, plans, and user-facing wrappers. orig-nv-eng Reported or requested by NVIDIA engineering.
#292 opened Jun 8, 2026 by saltyminty Collaborator Loading… Frontend 1.26.0
1
Use UID-based graph JSON v2 for repro extraction cat-infra Build, packaging, tooling, dependency, release, or repository maintenance work. mod-frontend cuDNN frontend APIs, operation graph construction, plans, and user-facing wrappers. orig-nv-eng Reported or requested by NVIDIA engineering.
#280 opened Jun 4, 2026 by hwanseoc Member Loading… Frontend 1.26.0
@hwanseoc
26
Limit graph heuristic config queries
#279 opened Jun 4, 2026 by yeliu-oss Loading…
7
Update conv get-plan sample heuristic config count
#278 opened Jun 4, 2026 by yeliu-oss Loading…
1
Vedaanta/sdpa d256 cudnn 9 23 bypass oss cat-enhancements mod-frontend cuDNN frontend APIs, operation graph construction, plans, and user-facing wrappers. orig-nv-eng Reported or requested by NVIDIA engineering.
#272 opened Jun 2, 2026 by vedaanta Collaborator Loading… Frontend 1.25.0
8
Add linear attention API cat-feature Requests for new functionality, APIs, examples, or behavior improvements.
#268 opened Jun 2, 2026 by jhjpark Loading…
1
Add NWH + B2B causal conv1d notebooks; refresh outputs
#246 opened May 20, 2026 by yeliu-oss Loading…
3
ProTip! Exclude everything labeled bug with -label:bug.