Morph MORPH
SIGN IN SIGN UP
dhruvhead / ao UNCLAIMED
0 0 1 Python

COMMITS

/ torchao/quantization/quant_primitives.py
test
January 29, 2025
S
Consolidate `ZeroPointDomain.NONE` & `None` zero point domains (#1556)
sanchitintel committed
7b0d2ce
January 25, 2025
D
add separate quantization primitives for float8 (#1597)
Daniel Vega-Myhre committed
47f96f1
January 14, 2025
A
Fix torch.intx support in FakeQuantizeConfig (#1544)
andrewor14 committed
b3deb16
December 16, 2024
H
gemlite integration in torchao (#1034)
HDCharles committed
603d908
November 14, 2024
H
support W4A8 Marlin kernel (#1113)
HandH1998 committed
06e69f6
November 13, 2024
J
Update torchao api reference and add contributor guide (#1255)
Jerry Zhang committed
39f16f4
November 12, 2024
A
Ruff Lint fixes (torchao/quantization) (#1244)
Apurva Jain committed
b2642fb
November 4, 2024
T
BF16 support for Quant-LLM kernel (#1147)
Tobias van der Werff committed
8c07d22
October 30, 2024
S
Subclass API (#966)
Scott Roy committed
581d8e0
October 15, 2024
A
Add generic fake quantized linear for QAT (#1020)
andrewor14 committed
48bc81c
October 10, 2024
A
Move and rename GranularityType -> Granularity (#1038)
andrewor14 committed
0f6bae5
September 12, 2024
J
Renaming fpx to floatx (#877)
Jerry Zhang committed
8236a87
September 7, 2024
M
Update the way scale is calculated for affine Symmetric (#805)
Mengtao Yuan committed
c6abf2b
September 6, 2024
J
Expose hqq through `uintx_weight_only` API (#786)
Jerry Zhang committed
0601b5c
D
[StaticQuant] add a linear observer class and test (#807)
Driss Guessous committed
422301b
September 5, 2024
A
Add static quant to float8 (#787)
Apurva Jain committed
a246d87
D
[StaticQuant] Update how block_size is calculated with Observers (#815)
Driss Guessous committed
a1b3e67
September 4, 2024
J
Add more information to quantized linear module and added some logs (#782)
Jerry Zhang committed
0987dd6
August 30, 2024
D
Add Float8 Weight Only and FP8 weight + dynamic activation (#740)
Driss Guessous committed
d0e6246
August 29, 2024
J
[reland] Refactor quant_llm to work with affine quantized tensor (#696) (#772)
Jerry Zhang committed
05224a9
August 28, 2024
A
[Experimental] Float8 support in AQT (#671)
Apurva Jain committed
0916b5b
J
Revert "Refactor quant_llm to work with affine quantized tensor" (#767)
Jerry Zhang committed
da8c5b9
J
Refactor quant_llm to work with affine quantized tensor (#696)
Jerry Zhang committed
0fed444
August 23, 2024
J
Use `torch.uint1` to `torch.uint7` for Uintx tensor subclass (#672)
Jerry Zhang committed
9a56e80
S
Fix docstring args names (#735)
Sergii Dymchenko committed
68e4643
August 15, 2024
M
Add HQQ support (#605)
mobicham committed
18e38f1
August 14, 2024
M
retry version guard fix (#679)
Mark Saroufim committed
1acd710
J
Add AffineQuantizedObserver (#650)
Jerry Zhang committed
6199f89
August 8, 2024
J
Add support for using AffineQuantizedTensor with `weights_only=True` (#630)
Jerry Zhang committed
433cd14
August 3, 2024
J
Unpin nightly version (#593)
Jerry Zhang committed
ed83ae2
July 17, 2024
A
Add cachemask variant for fake_quantize_affine (#500)
andrewor14 committed
03c4553
July 11, 2024
A
Add general fake_quantize_affine op (#492)
andrewor14 committed
2ed010a
July 3, 2024
J
Add more docs for int4_weight_only API that targets tinygemm (#469)
Jerry Zhang committed
a895699
July 2, 2024
J
Add decorator for custom op and inductor decomp registration (#434)
Jerry Zhang committed
d1e15b4
June 9, 2024
J
Move quant ops to utils.py (#331)
Jerry Zhang committed
8c8bc81
June 7, 2024
J
Move some util functions from quantization.utils to torchao.utils (#337)
Jerry Zhang committed
000a0fd
June 5, 2024
J
Refactor rest of tinygemm quant primitive ops (#321)
Jerry Zhang committed
03e2c9b
C
Wrap torch.ops.quantized_decomposed to improve import errors (#310)
cpuhrsch committed
1518f7d
June 3, 2024
C
Check dequantize_affine is idempotent (#309)
cpuhrsch committed
d75f450
May 25, 2024
M
Quantization Docstrings (#273)
Mark Saroufim committed
a7bc592
May 18, 2024
J
Fix quant_primitive dtype that caused perf regression (#253)
Jerry Zhang committed
e9e5fae
May 15, 2024
A
Match torch.fake_quantize numerics in 8da4w QAT (#229)
andrewor14 committed
cae3d82
A
Fix CI after quantize op change in PyTorch core (#244)
andrewor14 committed
3dd16c9
May 14, 2024
J
Enable dispatch to tinygemm int4 and int8 kernels for quantized tensor (#230)
Jerry Zhang committed
10da375
May 9, 2024
J
Add more options in choose_qparams_affine for tinygemm op (#227)
Jerry Zhang committed
b91b6be
May 8, 2024
J
Some follow up fixes for quant primitives (#220)
Jerry Zhang committed
63c5ac5
May 7, 2024
J
Unified AffineQuantizedTensor subclass (#214)
Jerry Zhang committed
f0bdc8f
May 3, 2024
J
`quantize_activation_per_token_absmax` use general quant primitives (#193)
Jerry Zhang committed
5364de6
J
Refactor tensor subclass API to also use paramterization (#146)
Jerry Zhang committed
2371ff8
J
Reduce memory usage for symmetric choose_qparams (#210)
Jerry Zhang committed
1d9fea9