COMMITS
/ torchao/experimental/kernels/cpu/aarch64/tests/test_bitpacking.cpp August 21, 2025
Z
Bitpack add functions for Uint8
Zeyu Song committed
April 1, 2025
S
Add LUT-based bitpacking for 1-4 bits
Scott Roy committed
November 8, 2024
A
8-bit packing support
Alexander Oleinikov committed
October 23, 2024
C
Introduce 7-bit quantization for Llama in torchchat.
c4lcut3c committed
October 17, 2024
S
Swap in faster uint6 bitpacking function
Scott Roy committed
October 16, 2024
C
Experimental 6-bit quantization for Llama in torchchat
c4lcut3c committed
October 8, 2024
S
Optimize 3-bit packing
Scott Roy committed
October 3, 2024
R
Introduce 6-bit quantization for Llama in torchchat
ramreddymounica committed
September 30, 2024
S
Add arm neon guards
Scott Roy committed
September 20, 2024
V
Introducing 1-bit quantization for Llama in torchchat (#910)
Vaishnavi Gupta committed
September 3, 2024
S
Add 5bit packing routines
Scott Roy committed
S
Add 2bit packing routines
Scott Roy committed
August 21, 2024
S
Update licenses in torchao/experimental
Scott Roy committed
August 7, 2024
S
Move lowbit universal kernels from torchaccel to torchao
Scott Roy committed