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

[Misc] format and refactor some examples (#16252)

Browse Source 
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
This commit is contained in:
Reid
2025-04-08 18:42:32 +08:00
committed by GitHub
parent 995e3d1f41
commit 7f00899ff7
13 changed files with 178 additions and 115 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/offline_inference/multilora_inference.py
View File

@@ -61,6 +61,7 @@ def process_requests(engine: LLMEngine,
"""Continuously process a list of prompts and handle the outputs."""
request_id = 0
print("-" * 50)
while test_prompts or engine.has_unfinished_requests():
if test_prompts:
prompt, sampling_params, lora_request = test_prompts.pop(0)
@@ -75,6 +76,7 @@ def process_requests(engine: LLMEngine,
for request_output in request_outputs:
if request_output.finished:
print(request_output)
print("-" * 50)
def initialize_engine() -> LLMEngine: