Skip to content
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

Do not split decoder checkpoint files #567

Merged
merged 5 commits into from
Apr 15, 2024
Merged

Do not split decoder checkpoint files #567

Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
bfa8fdb
feat(decoder): do not split checkpoint files
dacorvo Apr 15, 2024
c0eb63d
test(tnx): use cached configuration in LLama test
dacorvo Apr 15, 2024
a48ac96
fix(decoder): do not pad to batch_size if continuous batching
dacorvo Apr 15, 2024
0f0d622
fix: bump setuptools version
dacorvo Apr 15, 2024
6fb6f0e
fix(tgi): adapt to latest setuptools
dacorvo Apr 15, 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
Prev Previous commit
Next Next commit
test(tnx): use cached configuration in LLama test
  • Loading branch information
@dacorvo
dacorvo committed Apr 15, 2024
commit c0eb63db6b7f682ce49c2ee2c17499d9d1b366bb
2 changes: 1 addition & 1 deletion tests/generation/test_tnx_llama.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@
@requires_neuronx
def test_generation_llama_padded_inputs():
model_id = "NousResearch/Llama-2-7b-chat-hf"
model_kwargs = {"batch_size": 2, "sequence_length": 2048, "auto_cast_type": "f16", "num_cores": 2}
model_kwargs = {"batch_size": 4, "sequence_length": 4096, "auto_cast_type": "f16", "num_cores": 2}
model = NeuronModelForCausalLM.from_pretrained(model_id, export=True, **model_kwargs)
tokenizer = AutoTokenizer.from_pretrained(model_id)
prompt = "One of my fondest memory is of my grandmother making homemade bread"
Expand Down