Skip to content

Fix quantized embedding export logic #3095

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

Closed
wants to merge 4 commits into from
Closed

Fix quantized embedding export logic #3095

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
73d5e7e
{executorch][llama] support mqa
kimishpatel Apr 17, 2024
f7c1459
4b embedding quantizer (#3081)
Apr 17, 2024
f938acb
Patch
larryliu0820 Apr 17, 2024
a28e73b
Define embedding_4bit ops
larryliu0820 Apr 18, 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
5 changes: 4 additions & 1 deletion examples/models/llama2/export_llama_lib.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -539,7 +539,10 @@ def _prepare_for_llama_export(modelname: str, args) -> LlamaEdgeManager:
bitwidth = int(bitwidth)
transforms.append(
lambda model: EmbeddingQuantHandler(
model, bitwidth=bitwidth, group_size=group_size
model,
bitwidth=bitwidth,
group_size=group_size,
packed=(bitwidth == 4),
).quantized_model()
)

Expand Down
2 changes: 1 addition & 1 deletion exir/passes/_quant_patterns_and_replacements.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -189,7 +189,7 @@ def embedding_byte_dtype_out_meta(

quantized_decomposed_lib.define(
"embedding_4bit.dtype_out(Tensor weight, Tensor weight_scales, Tensor? weight_zero_points, "
"int weight_quant_min, int weight_quant_max, Tensor indices, ScalarType? dtype=None, *, Tensor(a!) out) -> Tensor(a!)",
"int weight_quant_min, int weight_quant_max, Tensor indices, *, ScalarType? dtype=None, Tensor(a!) out) -> Tensor(a!)",
)


Expand Down