ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

Support new fp8 e4m3 (#11158)

Browse source
This commit is contained in:
Yina Chen 2024-05-29 14:27:14 +08:00 committed by GitHub
parent 8e25de1126
commit e29e2f1c78
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
python/llm/src/ipex_llm/transformers/low_bit_linear.py
View file

@ -329,13 +329,14 @@ def use_batch_forward(x: torch.Tensor, qtype: int, output_len: int):
and output_len % 32 == 0
and device in ["arc", "flex", "pvc", "mtl"]
and qtype in [SYM_INT4, ASYM_INT4, SYM_INT8, FP4,
FP8E5, FP6]
FP8E5, FP6, FP8E4]
and batch_size <= 64
)
if hard_condition:
return (
batch_size > 1
or (device in ["arc", "flex"] and qtype in [SYM_INT8, FP4])
or (device in ["arc", "flex", "mtl"] and qtype in [FP8E4])
)
return False