[Cleanup] Remove online quantization support in fp8.py in favor of online shorthands (#53585)
Signed-off-by: Felix Marty <Felix.Marty@amd.com> Signed-off-by: mgoin <mgoin64@gmail.com> Co-authored-by: mgoin <mgoin64@gmail.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
mgoin
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent
58aa2f1ef1
commit
90a9515006
@@ -271,7 +271,6 @@ class TestMLAAttentionFp8GroupQuantPatternModel(MLAAttentionQuantPatternModel):
|
||||
|
||||
quant_key = kFp8Dynamic128Sym
|
||||
quant_config = Fp8Config(
|
||||
is_checkpoint_fp8_serialized=True,
|
||||
weight_block_size=[128, 128],
|
||||
)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user