Skip to content

Commit

Permalink
ci: update llm cache files
Browse files Browse the repository at this point in the history
  • Loading branch information
dacorvo committed Sep 26, 2024
1 parent c3eed64 commit 7a8e99c
Show file tree
Hide file tree
Showing 4 changed files with 6 additions and 94 deletions.
4 changes: 2 additions & 2 deletions .github/workflows/inference_cache_llm.yml
Original file line number Diff line number Diff line change
Expand Up @@ -21,9 +21,9 @@ jobs:
matrix:
config: [
gpt2,
llama3-8b,
llama,
llama3.1-70b,
llama3-70b,
llama2-7b-13b,
llama2-70b,
mistral,
llama-variants,
Expand Down
43 changes: 0 additions & 43 deletions benchmark/text-generation/llama2-7b.py

This file was deleted.

Original file line number Diff line number Diff line change
Expand Up @@ -8,16 +8,14 @@


def main():
NUM_CORES = 8
NUM_CORES = 12
num_cores = get_available_cores()
if num_cores < NUM_CORES:
raise ValueError(f"This benchmark can only run on an instance with at least {NUM_CORES} cores.")

model_configurations = {
"Llama-2-13B-BS1": ["meta-llama/Llama-2-13b-chat-hf", 1, 4096],
"Llama-2-13B-BS4": ["meta-llama/Llama-2-13b-chat-hf", 4, 4096],
"Llama-2-13B-BS8": ["meta-llama/Llama-2-13b-chat-hf", 8, 4096],
"Llama-2-13B-BS16": ["meta-llama/Llama-2-13b-chat-hf", 16, 4096],
"Mistral-Small-2409-BS1": ["mistralai/Mistral-Small-Instruct-2409", 1, 4096],
"Mistral-Small-2409-BS4": ["mistralai/Mistral-Small-Instruct-2409", 4, 4096],
}

for model_name, model_configuration in model_configurations.items():
Expand All @@ -27,7 +25,7 @@ def main():
export=True,
batch_size=batch_size,
sequence_length=seq_length,
auto_cast_type="fp16",
auto_cast_type="bf16",
num_cores=NUM_CORES,
)
with TemporaryDirectory() as tmpdir:
Expand Down
43 changes: 0 additions & 43 deletions benchmark/text-generation/mistralv2.py

This file was deleted.

0 comments on commit 7a8e99c

Please sign in to comment.