Skip to content

Issues: triton-lang/triton

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

717 Open 939 Closed
717 Open 939 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

python: ../../../lib/Dialect/TritonGPU/Transforms/AccelerateMatmul.cpp:36: int mlir::triton::gpu::(anonymous namespace)::getMMAVersionSafe(int, DotOp): Assertion `false && "computeCapability not supported"' failed. bug
#6087 opened Mar 3, 2025 by ruralharry
2
The python setup.py not support windows bug
#6081 opened Mar 1, 2025 by NOFOX
runtime JIT execution of the same kernel incurs high overhead(binder function) performance
#6064 opened Feb 28, 2025 by Learnmore666
6
Microscaling dtypes in triton?
#6054 opened Feb 28, 2025 by vkuzo
6
Triton incorrectly interprets uint8 indices as int8 in pointer arithmetic operations bug
#6043 opened Feb 27, 2025 by Ivan1248
3D tensor can't sum bug needs reproducer
#6039 opened Feb 27, 2025 by mdy666
Suggest adding/keeping range for input parameters
#6030 opened Feb 26, 2025 by bingyizh233
fused attention (flash attention v2) doesn't support bfloat16?
#6005 opened Feb 24, 2025 by guanzhchen
tl.sort and torch.sort give inconsistent results when input contains inf or nan bug
#5999 opened Feb 24, 2025 by chenmiao1919
2
Tensor Methods are Broken ("RuntimeError: Cannot call @triton.jit'd outside of the scope of a kernel") bug needs reproducer
#5994 opened Feb 22, 2025 by cora-codes
2
Matmul tutorial code failed on odd sizes with FP16 inputs bug
#5990 opened Feb 22, 2025 by yyong120
1
Addition Incorrect bug
#5972 opened Feb 20, 2025 by Phoveran
2
Bug in tutorials/06-fused-attention.py: test_op assertion fails for specific input. bug
#5971 opened Feb 20, 2025 by p81sunshine
Nightly install
#5967 opened Feb 19, 2025 by jeromeku
errors introduced by scalars in Interpreter mode bug
#5965 opened Feb 19, 2025 by hesse-x
@Jokeren
3
Dose Triton supports new features of Blackwell for RTX5090 and 5080?
#5950 opened Feb 18, 2025 by jt-zhang
4
Cache Modifier '.cs' Not Supported for LOAD
#5946 opened Feb 18, 2025 by huanggx-sea
Triton kernel not compiling with multiple threads and GPUs bug
#5933 opened Feb 15, 2025 by amnamasood-amd
1
Upstream LLVM SLP vectorizer change requires the correct triple performance
#5930 opened Feb 14, 2025 by pclove1
@Jokeren
fatal : Unsupported .version 8.6; current version is '8.5'
#5929 opened Feb 14, 2025 by nitinmukesh
f16 -> f8e5m2 conversion on H100 does not preserve infinities bug
#5927 opened Feb 14, 2025 by bchetioui
RTNE semantics are not respected by tt.fp_to_fp going from f16 to f8e5m2 on A100 bug
#5925 opened Feb 14, 2025 by bchetioui
SystemError: PY_SSIZE_T_CLEAN macro must be defined for '#' formats bug
#5919 opened Feb 14, 2025 by famiu
1
Performance Discrepancy Between Matrix Multiplication written in 3D and 2D Loads performance
#5916 opened Feb 13, 2025 by nullplay
2
tl.cumsum(i1) computes tl.cumsum_xor enhancement help wanted
#5897 opened Feb 12, 2025 by danthe3rd
4
ProTip! Follow long discussions with comments:>50.