Skip to content

Commit 09c7761

Browse files
Merge pull request #95 from andrea-fasoli/int8_sd_conversion
feat: Add int8 sd conversion function for aiu
2 parents 5a68c9e + 5d78549 commit 09c7761

4 files changed

Lines changed: 490 additions & 5 deletions

File tree

.pylintrc

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -63,7 +63,7 @@ ignore-patterns=^\.#
6363
# (useful for modules/projects where namespaces are manipulated during runtime
6464
# and thus existing member attributes cannot be deduced by static analysis). It
6565
# supports qualified module names, as well as Unix pattern matching.
66-
ignored-modules=auto_gptq,
66+
ignored-modules=auto_gptq,
6767
exllama_kernels,
6868
exllamav2_kernels,
6969
llmcompressor,
@@ -94,7 +94,7 @@ persistent=yes
9494

9595
# Minimum Python version to use for version dependent checks. Will default to
9696
# the version used to run pylint.
97-
py-version=3.9
97+
py-version=3.10
9898

9999
# Discover python modules and packages in the file system subtree.
100100
recursive=no

fms_mo/quant/quantizers.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -428,7 +428,7 @@ def set_quantizer(self):
428428
else:
429429
self.quantizer = SAWBSTE
430430

431-
def forward(self, input_tensor):
431+
def forward(self, input_tensor: torch.Tensor) -> torch.Tensor:
432432
input_tensor = self.quantizer.apply(
433433
input_tensor,
434434
self.num_bits,

0 commit comments

Comments
 (0)