Skip to content

Add Attention Quantization Examples #2484

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

Open
kylesayrs wants to merge 6 commits into
base: main
Choose a base branch
from
+23 −20
Open

Add Attention Quantization Examples #2484

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
830b53d
move examples
kylesayrs Mar 18, 2026
026fd14
update readmes
kylesayrs Mar 18, 2026
69e070b
Update examples/quantization_attention/README.md
kylesayrs Mar 19, 2026
b93b249
Merge branch 'main' into kylesayrs/kv-examples
dsikka Mar 23, 2026
649b9b8
Merge branch 'main' into kylesayrs/kv-examples
kylesayrs Mar 24, 2026
396f84d
Merge branch 'main' into kylesayrs/kv-examples
dsikka Mar 24, 2026
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
1 change: 1 addition & 0 deletions examples/quantization_attention/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
TODO, eval from eldar
2 changes: 1 addition & 1 deletion experimental/attention/llama3_attention.py → ...uantization_attention/llama3_attention.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
from compressed_tensors.offload import dispatch_model
from compressed_tensors.quantization import QuantizationArgs, QuantizationScheme
from datasets import load_dataset
from transformers import AutoModelForCausalLM, AutoTokenizer

from llmcompressor import oneshot
from llmcompressor.modifiers.quantization import QuantizationModifier
from compressed_tensors.offload import dispatch_model

# Select model and load it.
model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
Expand Down
Loading