Skip to content

Pull requests: NVIDIA/cudnn-frontend

New pull request New
30 Open 240 Closed
30 Open 240 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

Norm Samples updates for B,S,H style tensor inputs
#432 opened Jul 23, 2026 by rmhaskarnvidia Loading…
2 tasks done
5
Support mixed-form sequence lengths in SDPA forward (cuDNN 9.26+) cat-enhancements mod-frontend cuDNN frontend APIs, operation graph construction, plans, and user-facing wrappers. orig-nv-eng Reported or requested by NVIDIA engineering.
#430 opened Jul 23, 2026 by egilliam-nv Collaborator Loading…
2 tasks done
@egilliam-nv
3
Fix stream-ordering and input-validation holes in the SM100 DSA backward interface
#429 opened Jul 23, 2026 by zkyue Contributor Loading…
2 tasks done
1
CSA: add fused Compressor forward+backward CuTe-DSL kernels (ported from Megatron-LM)
#427 opened Jul 23, 2026 by zkyue Contributor Loading…
6
Fix a latent SMEM handoff race in the SM100 DSA indexer backward kernel
#426 opened Jul 23, 2026 by zkyue Contributor Loading…
2 tasks done
3
test_mhas_v2: extend bwd random head-dim coverage to d=256
#425 opened Jul 22, 2026 by vedaanta Collaborator Loading…
5
Support F64 compute data type for convolutions cat-enhancements mod-frontend cuDNN frontend APIs, operation graph construction, plans, and user-facing wrappers. orig-external Reported or requested by an external user, customer, or community contributor.
#423 opened Jul 22, 2026 by derdrdirk Loading… Frontend 1.27.0
@derdrdirk
4
DSA: fix SM100 sink normalization for 576/512 backward cat-bug Reports of incorrect behavior, crashes, regressions, or unexpected results. orig-nv-eng Reported or requested by NVIDIA engineering.
#421 opened Jul 22, 2026 by jiayus-nvidia Contributor Loading…
2 tasks
Frontend 1.27.0
1
@jiayus-nvidia
5
DSA indexer forward: add a lean SM100 fast path for the head_dim=128 / qhead_per_kv_head=64 regime (up to 1.46x)
#416 opened Jul 21, 2026 by zkyue Contributor Loading…
1
feat: add BF16 grouped GEMM MoE kernels cat-feature Requests for new functionality, APIs, examples, or behavior improvements. mod-cutedsl CuTeDSL kernels, generated kernels, examples, or related integration work.
#415 opened Jul 21, 2026 by saltyminty Collaborator Loading… Frontend 1.27.0
@saltyminty
14
Reject FP8/MXFP8 SDPA forward combinations exposed to a cuDNN 9.24 split-KV bug
#414 opened Jul 20, 2026 by vedaanta Collaborator Loading…
1
Add version-adaptive nvvm.atomicrmw wrapper for cutlass-dsl 4.5.x compat
#411 opened Jul 20, 2026 by Anerudhan Collaborator Loading…
1
1
Fix IMA caused by OOB lanes in varlen indexer top-k cat-bug Reports of incorrect behavior, crashes, regressions, or unexpected results. mod-cutedsl CuTeDSL kernels, generated kernels, examples, or related integration work. orig-nv-eng Reported or requested by NVIDIA engineering.
#410 opened Jul 20, 2026 by hxbai Loading…
2 tasks
Frontend 1.27.0
@hxbai
2
Use professional wording in env report docs
#409 opened Jul 20, 2026 by liujane-dev Collaborator Loading…
2 tasks done
@liujane-dev
3
Relicense to Apache-2.0 (dual-license; external-contributor files remain MIT)
#408 opened Jul 17, 2026 by Anerudhan Collaborator • Draft
1
DSA: fix 576-wide d_sink, test/document top-k index semantics, B300 benchmarks
#405 opened Jul 17, 2026 by vedaanta Collaborator Loading…
6
Support zero-element graphs (e.g. SDPA with batch size 0)
#404 opened Jul 17, 2026 by Anerudhan Collaborator • Draft
1
1
Support installing python bindings via cmake --install (fixes #149) cat-ci CI failures, test flakiness, workflow breakage, or automation issues. cat-infra Build, packaging, tooling, dependency, release, or repository maintenance work. mod-infra Infrastructure, CI/CD, build systems, packaging, releases, or repo maintenance. orig-external Reported or requested by an external user, customer, or community contributor.
#403 opened Jul 17, 2026 by Anerudhan Collaborator Loading… Frontend 1.27.0
1
@Anerudhan
4
Add large-tensor convolution fuzzer
#401 opened Jul 16, 2026 by msalasooNV Collaborator Loading…
@Anerudhan
6
Add FLOOR_MOD (floored modulo) pointwise mode cat-feature Requests for new functionality, APIs, examples, or behavior improvements. mod-backend cuDNN backend API, graph execution, descriptors, engines, or backend integration. orig-nv-eng Reported or requested by NVIDIA engineering.
#393 opened Jul 15, 2026 by vikramchandrashekar • Draft Frontend 1.27.0
@vikramchandrashekar
1
Add MoE + expert-parallel Python API surface, PyTorch reference, and tests
#389 opened Jul 14, 2026 by Anerudhan Collaborator Loading…
8
DSA: Add FP8/MXFP8 and compressed Top-K indexer paths
#370 opened Jul 9, 2026 by jiayus-nvidia Contributor • Draft
4
[DRAFT] Add framework-agnostic operator APIs with JAX support
#363 opened Jul 8, 2026 by mgoldfarb-nvidia • Draft
1
[DRAFT] Jax Support for FE OSS API
#351 opened Jul 6, 2026 by mgoldfarb-nvidia • Draft
12
benchmark: compute causal SDPA FLOP counts without allocating masks
#347 opened Jul 5, 2026 by fallintoplace Contributor Loading…
1
ProTip! Mix and match filters to narrow down what you’re looking for.