From 967eaba573ed208fe9c8e49d84b591b1180a93b5 Mon Sep 17 00:00:00 2001 From: pandyamarut Date: Fri, 9 Aug 2024 14:41:07 -0700 Subject: [PATCH] change to float Signed-off-by: pandyamarut --- README.md | 2 +- src/engine_args.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 1633a74..7c567c2 100644 --- a/README.md +++ b/README.md @@ -18,7 +18,7 @@ Deploy OpenAI-Compatible Blazing-Fast LLM Endpoints powered by the [vLLM](https: ### 1. UI for Deploying vLLM Worker on RunPod console: ![Demo of Deploying vLLM Worker on RunPod console with new UI](media/ui_demo.gif) -### 2. Worker vLLM `v1.1` with vLLM `0.5.3` now available under `stable` tags +### 2. Worker vLLM `v1.2.0` with vLLM `0.5.4` now available under `stable` tags Update v1.1 is now available, use the image tag `runpod/worker-v1-vllm:stable-cuda12.1.0`. ### 3. OpenAI-Compatible [Embedding Worker](https://github.com/runpod-workers/worker-infinity-embedding) Released diff --git a/src/engine_args.py b/src/engine_args.py index 0436de5..2f37696 100644 --- a/src/engine_args.py +++ b/src/engine_args.py @@ -15,7 +15,7 @@ DEFAULT_ARGS = { "disable_log_stats": os.getenv('DISABLE_LOG_STATS', 'False').lower() == 'true', "disable_log_requests": os.getenv('DISABLE_LOG_REQUESTS', 'False').lower() == 'true', - "gpu_memory_utilization": int(os.getenv('GPU_MEMORY_UTILIZATION', 0.9)), + "gpu_memory_utilization": float(os.getenv('GPU_MEMORY_UTILIZATION', 0.95)), "pipeline_parallel_size": int(os.getenv('PIPELINE_PARALLEL_SIZE', 1)), "tensor_parallel_size": int(os.getenv('TENSOR_PARALLEL_SIZE', 1)), "served_model_name": os.getenv('SERVED_MODEL_NAME', None),