biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix some bugs (#2689)

Browse Source
This commit is contained in:
zspo
2024-02-01 02:09:23 +08:00
committed by GitHub
parent d69ff0cbbb
commit c664b0e683
2 changed files with 8 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/engine/async_llm_engine.py
View File

@@ -296,6 +296,8 @@ class AsyncLLMEngine:
async frontend will be executed in a separate process as the
model workers.
log_requests: Whether to log the requests.
max_log_len: Maximum number of prompt characters or prompt ID numbers
being printed in log.
start_engine_loop: If True, the background task to run the engine
will be automatically started in the generate call.
*args: Arguments for LLMEngine.
@@ -431,8 +433,8 @@ class AsyncLLMEngine:
logger.info(f"Received request {request_id}: "
f"prompt: {shortened_prompt!r}, "
f"prefix_pos: {prefix_pos},"
f"sampling params: {sampling_params}, "
f"prompt token ids: {shortened_token_ids}, "
f"sampling_params: {sampling_params}, "
f"prompt_token_ids: {shortened_token_ids}, "
f"lora_request: {lora_request}.")
if not self.is_running: