Skip to content

add hasattr check for torch fp8 dtype #1985

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 1 commit into from
Aug 29, 2024
Merged

add hasattr check for torch fp8 dtype #1985

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
add hasattr check for torch fp8 dtype 
Signed-off-by: xin3he <[email protected]>
  • Loading branch information
@xin3he
xin3he committed Aug 23, 2024
commit 1e9d4188b259878ee825ccac901bb4b36cf99686
18 changes: 12 additions & 6 deletions neural_compressor/torch/algorithms/weight_only/utility.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,12 +93,18 @@

FLOAT_MAPPING = {"nf4": NF4, "fp4": FP4_BNB, "fp4_e2m1_bnb": FP4_BNB, "fp4_e2m1": FP4_E2M1}
INT_MAPPING = {"nf4": NF4_BIT, "fp4": FP4_BNB_BIT, "fp4_e2m1_bnb": FP4_BNB_BIT, "fp4_e2m1": FP4_E2M1_BIT}
FP8_MAPPING = {
"fp8_e5m2": torch.float8_e5m2,
"fp8_e5m2fnuz": torch.float8_e5m2fnuz,
"fp8_e4m3fn": torch.float8_e4m3fn,
"fp8_e4m3fnuz": torch.float8_e4m3fnuz,
}
if hasattr(torch, "float8_e5m2") and hasattr(torch, "float8_e4m3fn"):
FP8_MAPPING = {
"fp8_e5m2": torch.float8_e5m2,
"fp8_e4m3fn": torch.float8_e4m3fn,
}
if hasattr(torch, "float8_e5m2fnuz") and hasattr(torch, "float8_e4m3fnuz"):
FP8_MAPPING = {
"fp8_e5m2": torch.float8_e5m2,
"fp8_e4m3fn": torch.float8_e4m3fn,
"fp8_e5m2fnuz": torch.float8_e5m2fnuz,
"fp8_e4m3fnuz": torch.float8_e4m3fnuz,
}


def quantize_4bit(tensor, quantile=1.0, dtype="nf4", return_int=False, **kwargs):
Expand Down