Spaces:
Paused
Paused
Update Dockerfile
Browse files- Dockerfile +1 -7
Dockerfile
CHANGED
|
@@ -38,10 +38,4 @@ RUN vllm -v
|
|
| 38 |
|
| 39 |
# RUN vllm serve unsloth/Llama-3.2-1B-bnb-4bit --host 0.0.0.0 --port 7860 --cpu-num-threads 2
|
| 40 |
# CMD ["vllm serve unsloth/Llama-3.2-1B-bnb-4bit --host 0.0.0.0 --port 7860"]
|
| 41 |
-
|
| 42 |
-
--model "unsloth/Llama-3.2-1B-bnb-4bit" \
|
| 43 |
-
--host 0.0.0.0 \
|
| 44 |
-
--port 7860 \
|
| 45 |
-
--tensor-parallel-size 1 \
|
| 46 |
-
--gpu-memory-utilization 0.0 \
|
| 47 |
-
--num-cpu-threads 2
|
|
|
|
| 38 |
|
| 39 |
# RUN vllm serve unsloth/Llama-3.2-1B-bnb-4bit --host 0.0.0.0 --port 7860 --cpu-num-threads 2
|
| 40 |
# CMD ["vllm serve unsloth/Llama-3.2-1B-bnb-4bit --host 0.0.0.0 --port 7860"]
|
| 41 |
+
RUN python3 -u -m vllm.entrypoints.openai.api_server --model "unsloth/Llama-3.2-1B-bnb-4bit" --host 0.0.0.0 --port 7860 --tensor-parallel-size 1 --gpu-memory-utilization 0.0 --num-cpu-threads 2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|