Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix: address ruff unsued vars lint

This commit is contained in:
David Holtz 2024-10-09 18:58:35 +00:00
parent 1ddde382bd
commit 247033b45f
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
server/tests/models/test_flash_causal_lm.py
View File

@ -58,7 +58,7 @@ def flash_causal_lm_warmup():
available_memory_after_model_and_tokenizer - current_memory available_memory_after_model_and_tokenizer - current_memory
) )
model_and_tokenizer_memory_mb = model_and_tokenizer_memory / 1024 / 1024 model_and_tokenizer_memory_mb = model_and_tokenizer_memory / 1024 / 1024
print(f"Model and Tokenizer memory: {model_and_tokenizer_memory}") print(f"Model and Tokenizer memory: {model_and_tokenizer_memory_mb}")
default_pb_parameters = generate_pb2.NextTokenChooserParameters( default_pb_parameters = generate_pb2.NextTokenChooserParameters(
temperature=0.9, temperature=0.9,
@ -150,6 +150,7 @@ def flash_causal_lm_warmup():
warmup_response = generate_pb2.WarmupResponse( warmup_response = generate_pb2.WarmupResponse(
max_supported_total_tokens=max_supported_total_tokens max_supported_total_tokens=max_supported_total_tokens
) )
print(warmup_response)
if __name__ == "__main__": if __name__ == "__main__":