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 16, 00:45 UTC
[V1] Include Engine Version in Logs (#12496)
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Robert Shaw committed
Jan 28, 2025 at 03:27 UTC
e29d4358ef054163b80dfb7e53ce3eb0e08d1328
2 files changed
+2
-2
vllm/engine/llm_engine.py
+1
-1
@@ -230,7 +230,7 @@ class LLMEngine:
230
)
231
232
logger.info(
233
- "Initializing an LLM engine (v%s) with config: %s, "
233
+ "Initializing a V0 LLM engine (v%s) with config: %s, "
234
"use_cached_outputs=%s, ",
235
VLLM_VERSION,
236
vllm_config,
vllm/v1/engine/core.py
+1
-1
@@ -42,7 +42,7 @@ class EngineCore:
42
):
43
assert vllm_config.model_config.runner_type != "pooling"
44
45
- logger.info("Initializing an LLM engine (v%s) with config: %s",
45
+ logger.info("Initializing a V1 LLM engine (v%s) with config: %s",
46
VLLM_VERSION, vllm_config)
47
48
# Setup Model.