COMMITS
/ setup.py March 18, 2025
A
Remove duplicated code from setup.py (#1904)
Aleksandar Samardžić committed
March 13, 2025
A
Add CUTLASS-based row-wise scaled sparse FP8 kernel (#1671)
Aleksandar Samardžić committed
March 5, 2025
S
Fix CI (#1837)
Scott Roy committed
J
ROCm Sparse Marlin Kernels #1206 (#1834)
Jesse Cai committed
March 4, 2025
J
ruff fix for setup.py (#1833)
Jesse Cai committed
P
ROCm Support : Tile_Layout kernel (#1201)
Peter Yeh committed
S
Optionally enable KleidiAI + clean up setup.py flags (#1826)
Scott Roy committed
March 1, 2025
M
metal lowbit kernels: pip install (#1785)
Manuel Candales committed
February 20, 2025
J
Remove duplicate, confusing conditional in setup.py (#1748)
Jane (Yuan) Xu committed
S
Add ukernel selection logic + clean up KleidiAI integration (#1652)
Scott Roy committed
February 12, 2025
D
Add mx_fp8_bf16 kernel (#1637)
Driss Guessous committed
February 5, 2025
T
Add CUTLASS-based W4A4 (#1515)
Thien Tran committed
January 27, 2025
J
Prepare for -DPy_LIMITED_API flag in pytorch #145764 (#1627)
Jane (Yuan) Xu committed
January 13, 2025
A
Verify that submodules are checked out (#1536)
Aleksandar Samardžić committed
January 10, 2025
S
torchao setup.py with cmake
Scott Roy committed
January 8, 2025
A
Lint ao (#1521)
Apurva Jain committed
January 5, 2025
A
W4A8 based on CUTLASS (#880)
Aleksandar Samardžić committed
December 19, 2024
J
Set the url to pytorch/ao and clean up some duplication (#1446)
Jane (Yuan) Xu committed
J
[2/2] Switch ao to use py_limited_api (#1277)
Jane (Yuan) Xu committed
November 13, 2024
J
[1/2] Wean off of PYBIND in favor of torch.ops.load_library (#1276)
Jane (Yuan) Xu committed
August 16, 2024
A
Remove torchao_nightly package (#661)
Andrey Talman committed
July 31, 2024
M
Add git version suffix to package name (#547)
Mark Saroufim committed
June 27, 2024
M
remove torch dependency (#449)
Mark Saroufim committed
June 18, 2024
T
Add support for building CUDA extension on Windows (#396)
Thien Tran committed
June 17, 2024
M
Remove all dependencies except torch (#369)
Mark Saroufim committed
June 15, 2024
M
use pytorch version env variable (#373)
Mark Saroufim committed
June 12, 2024
M
Update version to 0.3.0 (#348)
Mark Saroufim committed
June 10, 2024
T
FP6-LLM clean up (again) (#339)
Thien Tran committed
June 9, 2024
M
Revert "Clean up FP6-LLM" (#338)
Mark Saroufim committed
T
Clean up FP6-LLM (#304)
Thien Tran committed
May 30, 2024
M
Graceful handling of cpp extensions (#296)
Mark Saroufim committed
May 29, 2024
A
Add suffix to package version (#293)
Andrey Talman committed
May 25, 2024
T
Improve primitives for FP6 quant (#248)
Thien Tran committed
May 14, 2024
T
Add FP16Act-FP6Weight Linear (#223)
Thien Tran committed
May 9, 2024
C
Bump version to 0.2.0 (#234)
cpuhrsch committed
April 29, 2024
M
louder warning + docs for custom cuda extensions (#186)
Mark Saroufim committed
April 26, 2024
M
Custom CUDA extensions (#135)
Mark Saroufim committed
April 16, 2024
J
GaLore and fused kernel prototypes (#95)
jeromeku committed
April 4, 2024
J
torchao v0.1 version bump (#125)
Jerry Zhang committed
March 21, 2024
C
Autotuner for int mm Triton kernels (#41)
cpuhrsch committed
March 13, 2024
M
Fix Nightly build script (#54)
Mark Saroufim committed
January 4, 2024
H
0.0.3 release
HDCharles committed
H
0.0.2 release
HDCharles committed
January 3, 2024
H
aligning release in github and pypi
HDCharles committed
H
Update setup.py
HDCharles committed
November 10, 2023
C
Even smaller version
Christian Puhrsch committed
C
Move ao to torchao
Christian Puhrsch committed
C
Update setup.py
cpuhrsch committed
November 7, 2023
H
Adding gpu quantization workflows and apis
HDCharles committed