Skip to content

Issues: tracel-ai/cubecl

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

49 Open 28 Closed
49 Open 28 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
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Bug in lined f16 code
#386 opened Dec 19, 2024 by torsteingrindvik
Line support for saturating sub
#385 opened Dec 19, 2024 by torsteingrindvik
1
Primitive casting does not work for some primitives
#382 opened Dec 18, 2024 by torsteingrindvik
1
1
Problem compiling CUDA code with new const
#379 opened Dec 17, 2024 by torsteingrindvik
Support assignation for types other than CubePrimitive
#364 opened Dec 10, 2024 by maxtremblay
Matrix Multiplication: Cmma Matrix Double Buffering
#358 opened Dec 9, 2024 by nathanielsimard
Feature: Recursive Types
#357 opened Dec 9, 2024 by nathanielsimard
2
Add ability to get hold of ComputeClient when using existing wgpu setup
#355 opened Dec 6, 2024 by torsteingrindvik
Remove vectorization in favor of lines
#354 opened Dec 6, 2024 by maxtremblay
5 tasks
Improve and uniformize naming documentation Improvements or additions to documentation enhancement New feature or request
#353 opened Dec 6, 2024 by maxtremblay
21 tasks
Make wgpu runtime with SPIR-V compiler to work on MacOS
#341 opened Dec 3, 2024 by syl20bnr
#[cube] impl blocks do not use spans to show where problems are
#334 opened Dec 1, 2024 by torsteingrindvik
Compile error in cube type impl if struct behind conditional
#333 opened Dec 1, 2024 by torsteingrindvik
Allow using atomic types as launch args
#328 opened Nov 29, 2024 by torsteingrindvik
Direct buffer passing
#291 opened Nov 22, 2024 by leizaf
1
Feature flag for opt-in/opt-out of checked launches
#266 opened Nov 16, 2024 by torsteingrindvik
2
Subcube elect doesn't work with wgpu
#254 opened Nov 12, 2024 by maxtremblay
MemoryManagement<Storage>::reserve() can panic with index out of bounds bug Something isn't working
#243 opened Nov 10, 2024 by Quba1
1
2
Compilation Bug: the cuda code generated from gelu example fails to compile without -std=c++11 bug Something isn't working
#226 opened Nov 5, 2024 by BurtonQin
1
More docs for discoverability of which choices for vectorization are ok
#222 opened Nov 1, 2024 by torsteingrindvik
2
Unchecked kernel launch should precisely state the safety contract documentation Improvements or additions to documentation good first issue Good for newcomers
#217 opened Oct 30, 2024 by torsteingrindvik
Packed types support {u,i}16, {u,i}8
#166 opened Oct 11, 2024 by andreytkachenko
1
Support cuMemcpy2D with stride (pitch)
#165 opened Oct 11, 2024 by andreytkachenko
Support Int4/Int8.. Type
#162 opened Oct 10, 2024 by AntiAnimeGeneral
1
More vector functions
#135 opened Sep 19, 2024 by RianGoossens
1 of 3 tasks
ProTip! Type g i on any issue or pull request to go back to the issue listing page.