A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 04:15 UTC
Add tqdm `dynamic_ncols=True` (#3242)
Chujie Zheng committed
Mar 6, 2024 at 14:41 UTC
4cb3b924cdeb6b809f0a0311f9833253d9162699
1 file changed
+3
-1
vllm/entrypoints/llm.py
+3
-1
@@ -191,7 +191,9 @@ class LLM:
191
# Initialize tqdm.
192
if use_tqdm:
193
num_requests = self.llm_engine.get_num_unfinished_requests()
194
- pbar = tqdm(total=num_requests, desc="Processed prompts")
194
+ pbar = tqdm(total=num_requests,
195
+ desc="Processed prompts",
196
+ dynamic_ncols=True)
197
# Run the engine.
198
outputs: List[RequestOutput] = []
199
while self.llm_engine.has_unfinished_requests():