xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 04:05:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] improve logits processors logging message (#7435)

Browse Source
This commit is contained in:
Andrew Wang 2024-08-12 19:29:34 -07:00 committed by GitHub
parent 9ba85bc152
commit 97a6be95ba
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
tests/entrypoints/openai/test_serving_chat.py
View File

@ -73,7 +73,6 @@ def test_serving_chat_should_set_correct_max_tokens():
with suppress(Exception): with suppress(Exception):
asyncio.run(serving_chat.create_chat_completion(req)) asyncio.run(serving_chat.create_chat_completion(req))
# AsyncLLMEngine.generate(inputs, sampling_params, ...)
assert mock_engine.generate.call_args.args[1].max_tokens == 93 assert mock_engine.generate.call_args.args[1].max_tokens == 93
req.max_tokens = 10 req.max_tokens = 10

2
vllm/entrypoints/openai/logits_processors.py
View File

@ -71,7 +71,7 @@ def get_logits_processors(
# Check if token_id is within the vocab size # Check if token_id is within the vocab size
for token_id, bias in clamped_logit_bias.items(): for token_id, bias in clamped_logit_bias.items():
if token_id < 0 or token_id >= tokenizer.vocab_size: if token_id < 0 or token_id >= tokenizer.vocab_size:
raise ValueError("token_id in logit_bias contains " raise ValueError(f"token_id {token_id} in logit_bias contains "
"out-of-vocab token id") "out-of-vocab token id")
logits_processors.append( logits_processors.append(