Hugging Face's logo

Spaces:
yusufs
/
vllm-inference
Paused

App Files
yusufs commited on
Commit
cb15911
·
1 Parent(s): 266e7dd

fix(runner.sh): --enforce-eager not support values

Browse files
Files changed (3) hide show
  1. run-llama.sh +0 -1
  2. run-sailor.sh +0 -1
  3. runner.sh +0 -1
run-llama.sh CHANGED
@@ -27,5 +27,4 @@ python -u /app/openai_compatible_api_server.py \
27
  --max-num-batched-tokens 32768 \
28
  --max-model-len 32768 \
29
  --dtype float16 \
30
- --enforce-eager false \
31
  --gpu-memory-utilization 0.85
 
27
  --max-num-batched-tokens 32768 \
28
  --max-model-len 32768 \
29
  --dtype float16 \
 
30
  --gpu-memory-utilization 0.85
run-sailor.sh CHANGED
@@ -29,5 +29,4 @@ python -u /app/openai_compatible_api_server.py \
29
  --max-num-batched-tokens 32768 \
30
  --max-model-len 32768 \
31
  --dtype float16 \
32
- --enforce-eager false \
33
  --gpu-memory-utilization 0.85
 
29
  --max-num-batched-tokens 32768 \
30
  --max-model-len 32768 \
31
  --dtype float16 \
 
32
  --gpu-memory-utilization 0.85
runner.sh CHANGED
@@ -51,5 +51,4 @@ python -u /app/openai_compatible_api_server.py \
51
  --max-num-batched-tokens 32768 \
52
  --max-model-len 32768 \
53
  --dtype float16 \
54
- --enforce-eager false \
55
  --gpu-memory-utilization 0.9
 
51
  --max-num-batched-tokens 32768 \
52
  --max-model-len 32768 \
53
  --dtype float16 \
 
54
  --gpu-memory-utilization 0.9