Skip to content

Update AutoRound commit version #1941

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 8 commits into from
Jul 23, 2024
Merged

Update AutoRound commit version #1941

Changes from 1 commit
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
a1feaf5
update commit version
Kaihui-intel Jul 19, 2024
967b780
Merge branch 'master' into kaihui/ar_v0.3
chensuyue Jul 22, 2024
e538a63
update int4 usage
Kaihui-intel Jul 22, 2024
ad7ac9d
update commit version
Kaihui-intel Jul 23, 2024
f7cfe72
add int4 ut
Kaihui-intel Jul 23, 2024
650d435
update config
Kaihui-intel Jul 23, 2024
b935abf
Merge branch 'master' into kaihui/ar_v0.3
Kaihui-intel Jul 23, 2024
0d3d257
merge master
Kaihui-intel Jul 23, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
update int4 usage 
Signed-off-by: Kaihui-intel <[email protected]>
  • Loading branch information
@Kaihui-intel
Kaihui-intel committed Jul 22, 2024
commit e538a63110b71c303bcceef265b7acaeed9df5f2
9 changes: 7 additions & 2 deletions neural_compressor/torch/quantization/algorithm_entry.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -567,9 +567,14 @@ def autoround_quantize_entry(
if quant_config.name != AUTOROUND or quant_config.dtype == "fp32":
continue
else:
dtype = quant_config.dtype
bits = quant_config.bits
if dtype != "int" and "int" in dtype:
bits = int(dtype.lstrip("int"))
dtype = "int"
weight_config[op_name] = {
"data_type": quant_config.dtype,
"bits": quant_config.bits,
"data_type": dtype,
"bits": bits,
"sym": quant_config.use_sym,
"group_size": quant_config.group_size,
"act_bits": quant_config.act_bits,
Expand Down