COMMITS
/ torchao/quantization/utils.py December 17, 2024
M
Expose zero_point_domain as arguments (#1401)
Meng, Hengyu committed
November 27, 2024
Y
Add Int4CPULayout and update int4 woq (#1278)
YanbingJiang committed
November 13, 2024
J
Update torchao api reference and add contributor guide (#1255)
Jerry Zhang committed
November 12, 2024
A
Ruff Lint fixes (torchao/quantization) (#1244)
Apurva Jain committed
October 7, 2024
M
Use `importlib.util.find_spec` to check if `lm_eval` is installed instead of trying to import it (#1023)
Matthew Hoffman committed
September 7, 2024
M
Update the way scale is calculated for affine Symmetric (#805)
Mengtao Yuan committed
September 5, 2024
H
int4 fixes and improvements (#804)
HDCharles committed
August 29, 2024
J
[reland] Refactor quant_llm to work with affine quantized tensor (#696) (#772)
Jerry Zhang committed
August 28, 2024
J
Revert "Refactor quant_llm to work with affine quantized tensor" (#767)
Jerry Zhang committed
J
Refactor quant_llm to work with affine quantized tensor (#696)
Jerry Zhang committed
August 14, 2024
M
retry version guard fix (#679)
Mark Saroufim committed
August 3, 2024
J
Unpin nightly version (#593)
Jerry Zhang committed
July 29, 2024
M
[int4-quant] Execute weights shuffling on CPU until MPS memory issue is resolved (#552)
Manuel Candales committed
Y
Fix int4pack_mm error (#517)
YanbingJiang committed
July 22, 2024
A
Refactor QAT to use common fake_quantize_affine primitive (#527)
andrewor14 committed
July 16, 2024
J
Skip tests broken by change of `_convert_weight_to_int4pack` (#504)
Jerry Zhang committed
July 5, 2024
M
Allow Int4WeightOnlyQuantizer to set different dtype for scales_and_zeros (#479)
Mengwei Liu committed
June 26, 2024
J
Fix f-string typo (#441)
Jerry Zhang committed
June 25, 2024
H
adding default inductor config settings (#423)
HDCharles committed
June 9, 2024
J
Move quant ops to utils.py (#331)
Jerry Zhang committed
June 7, 2024
J
Move some util functions from quantization.utils to torchao.utils (#337)
Jerry Zhang committed
June 5, 2024
C
Wrap torch.ops.quantized_decomposed to improve import errors (#310)
cpuhrsch committed
June 4, 2024
J
Refactor int4 and int8 weight only quantization to use `quantize` (#301)
Jerry Zhang committed
May 31, 2024
J
Refactor int8 dynamic quantization with call to `quantize` (#294)
Jerry Zhang committed
May 28, 2024
A
Extract eval code from GPTQ for more general usage (#275)
andrewor14 committed
May 25, 2024
M
Quantization Docstrings (#273)
Mark Saroufim committed
May 24, 2024
J
Add `quantize` (#256)
Jerry Zhang committed
May 23, 2024
M
FP8 splitgemm user defined triton kernel (#263)
Mark Saroufim committed
April 3, 2024
H
add int4 gptq and eval (#116)
HDCharles committed
March 30, 2024
C
Expand CI coverage to 2.2.2, 2.3rc and nightly (#96)
cpuhrsch committed
March 29, 2024
J
Change quantization version check to use 2.3.0.dev (#99)
Jerry Zhang committed
March 24, 2024
J
Move some quantization ops to pytorch (#77)
Jerry Zhang committed
March 22, 2024
C
Much lint, so wow (#76)
cpuhrsch committed
March 15, 2024
G
suppress errors in `pytorch`
generatedunixname89002005307016 committed
December 12, 2023
H
fixes to move to fbcode
HDCharles committed
November 28, 2023
H
Adding int4 quantized tensor subclass
HDCharles committed
November 10, 2023
C
Move ao to torchao
Christian Puhrsch committed