Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / mayank31398/cute-kernels issues and pull requests

#84 - embedding cuda

Pull Request - State: open - Opened by mayank31398 about 2 months ago

#84 - embedding cuda

Pull Request - State: open - Opened by mayank31398 about 2 months ago

#83 - compileable torch_custom_op

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#83 - compileable torch_custom_op

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#82 - rename files

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#82 - rename files

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#81 - embedding backward

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#81 - embedding backward

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#80 - function cleanup

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#79 - swiglu

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#78 - drop compile decorators

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#78 - drop compile decorators

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#77 - default cute config

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#77 - default cute config

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#76 - contiguous rmsnorm

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#76 - contiguous rmsnorm

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#75 - embedding contiguous

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#75 - embedding contiguous

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#74 - add_tensor

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#74 - add_tensor

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#73 - add readme

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#72 - add rmsnorm equations

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#71 - contiguous

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#71 - contiguous

Pull Request - State: closed - Opened by mayank31398 about 2 months ago

#70 - drop naive

Pull Request - State: closed - Opened by mayank31398 2 months ago

#70 - drop naive

Pull Request - State: closed - Opened by mayank31398 2 months ago

#69 - rename repo

Pull Request - State: closed - Opened by mayank31398 2 months ago

#69 - rename repo

Pull Request - State: closed - Opened by mayank31398 2 months ago

#68 - contiguous count kernel

Pull Request - State: closed - Opened by mayank31398 2 months ago

#68 - contiguous count kernel

Pull Request - State: closed - Opened by mayank31398 2 months ago

#67 - Rmsnorm backward with better partioning

Pull Request - State: closed - Opened by mayank31398 2 months ago

#67 - Rmsnorm backward with better partioning

Pull Request - State: closed - Opened by mayank31398 2 months ago

#66 - RMSNorm backward

Pull Request - State: closed - Opened by mayank31398 2 months ago

#66 - RMSNorm backward

Pull Request - State: closed - Opened by mayank31398 2 months ago

#65 - move add tests

Pull Request - State: closed - Opened by mayank31398 2 months ago

#64 - Fullgraph cutotune

Pull Request - State: closed - Opened by mayank31398 2 months ago

#63 - better triton kernels

Pull Request - State: closed - Opened by mayank31398 2 months ago

#63 - better triton kernels

Pull Request - State: closed - Opened by mayank31398 2 months ago

#62 - Cleanup

Pull Request - State: closed - Opened by mayank31398 2 months ago

#61 - Swiglu cuda vectorized backward

Pull Request - State: closed - Opened by mayank31398 2 months ago

#61 - Swiglu cuda vectorized backward

Pull Request - State: closed - Opened by mayank31398 2 months ago

#60 - Swiglu cuda vector instructions

Pull Request - State: closed - Opened by mayank31398 2 months ago

#59 - Scalar add

Pull Request - State: closed - Opened by mayank31398 2 months ago

#59 - Scalar add

Pull Request - State: closed - Opened by mayank31398 2 months ago

#58 - Add vectorized param

Pull Request - State: closed - Opened by mayank31398 2 months ago

#57 - swiglu kernel

Pull Request - State: closed - Opened by mayank31398 2 months ago

#57 - swiglu kernel

Pull Request - State: closed - Opened by mayank31398 2 months ago

#56 - Vector cleanup for tensor add

Pull Request - State: closed - Opened by mayank31398 2 months ago

#56 - Vector cleanup for tensor add

Pull Request - State: closed - Opened by mayank31398 2 months ago

#55 - vector_instruction_width for scalar add

Pull Request - State: closed - Opened by mayank31398 2 months ago

#55 - vector_instruction_width for scalar add

Pull Request - State: closed - Opened by mayank31398 2 months ago

#54 - rename vectorized_loop_size

Pull Request - State: closed - Opened by mayank31398 2 months ago

#54 - rename vectorized_loop_size

Pull Request - State: closed - Opened by mayank31398 2 months ago

#53 - use right shift

Pull Request - State: closed - Opened by mayank31398 2 months ago

#53 - use right shift

Pull Request - State: closed - Opened by mayank31398 2 months ago

#52 - Compileable C++

Pull Request - State: closed - Opened by mayank31398 3 months ago

#51 - Better Cutotune

Pull Request - State: closed - Opened by mayank31398 3 months ago

#51 - Better Cutotune

Pull Request - State: closed - Opened by mayank31398 3 months ago

#50 - Triton cleanup

Pull Request - State: closed - Opened by mayank31398 3 months ago

#50 - Triton cleanup

Pull Request - State: closed - Opened by mayank31398 3 months ago

#49 - word embeddings

Pull Request - State: closed - Opened by mayank31398 3 months ago

#49 - word embeddings

Pull Request - State: closed - Opened by mayank31398 3 months ago

#48 - CutoTune

Pull Request - State: closed - Opened by mayank31398 3 months ago

#48 - CutoTune

Pull Request - State: closed - Opened by mayank31398 3 months ago

#47 - Remove dependency on padded indices

Pull Request - State: closed - Opened by shawntan 3 months ago

#47 - Remove dependency on padded indices

Pull Request - State: closed - Opened by shawntan 3 months ago

#46 - T

Pull Request - State: closed - Opened by mayank31398 3 months ago

#46 - T

Pull Request - State: closed - Opened by mayank31398 3 months ago

#45 - Swiglu CUDA backward

Pull Request - State: closed - Opened by mayank31398 3 months ago

#45 - Swiglu CUDA backward

Pull Request - State: closed - Opened by mayank31398 3 months ago

#44 - custom dtype dispatcher

Pull Request - State: closed - Opened by mayank31398 4 months ago

#43 - pass by reference

Pull Request - State: closed - Opened by mayank31398 4 months ago

#43 - pass by reference

Pull Request - State: closed - Opened by mayank31398 4 months ago

#42 - change tensor layout for FSDP-2

Pull Request - State: closed - Opened by mayank31398 4 months ago - 1 comment

#42 - change tensor layout for FSDP-2

Pull Request - State: closed - Opened by mayank31398 4 months ago - 1 comment

#41 - torch custom op cleanup

Pull Request - State: closed - Opened by mayank31398 4 months ago

#41 - torch custom op cleanup

Pull Request - State: closed - Opened by mayank31398 4 months ago

#40 - torch custom op

Pull Request - State: closed - Opened by mayank31398 4 months ago

#40 - torch custom op

Pull Request - State: closed - Opened by mayank31398 4 months ago

#39 - Improvement of Scatter Kernels

Pull Request - State: closed - Opened by fabianlim 4 months ago

#39 - Improvement of Scatter Kernels

Pull Request - State: closed - Opened by fabianlim 4 months ago

#38 - cleanup throughput file

Pull Request - State: closed - Opened by mayank31398 4 months ago

#38 - cleanup throughput file

Pull Request - State: closed - Opened by mayank31398 4 months ago

#37 - scalar add

Pull Request - State: closed - Opened by mayank31398 4 months ago

#37 - scalar add

Pull Request - State: closed - Opened by mayank31398 4 months ago

#36 - move logic

Pull Request - State: closed - Opened by mayank31398 4 months ago

#36 - move logic

Pull Request - State: closed - Opened by mayank31398 4 months ago

#35 - use LIBRARY_NAME

Pull Request - State: closed - Opened by mayank31398 4 months ago

#35 - use LIBRARY_NAME

Pull Request - State: closed - Opened by mayank31398 4 months ago

#34 - Compileable scattermoe

Pull Request - State: closed - Opened by mayank31398 4 months ago

#34 - Compileable scattermoe

Pull Request - State: closed - Opened by mayank31398 4 months ago

#33 - avoid using heuristics

Pull Request - State: closed - Opened by mayank31398 4 months ago

#33 - avoid using heuristics

Pull Request - State: closed - Opened by mayank31398 4 months ago

#32 - drop record_function

Pull Request - State: closed - Opened by mayank31398 4 months ago

#32 - drop record_function

Pull Request - State: closed - Opened by mayank31398 4 months ago

#31 - ScatterMoE compile

Pull Request - State: closed - Opened by mayank31398 4 months ago

#31 - ScatterMoE compile

Pull Request - State: closed - Opened by mayank31398 4 months ago

#30 - move logic to python for better torch compile

Pull Request - State: closed - Opened by mayank31398 4 months ago

#29 - Drop mem efficient

Pull Request - State: closed - Opened by mayank31398 4 months ago

#28 - add ops.py

Pull Request - State: closed - Opened by mayank31398 4 months ago