Commit
•
680ef7a
1
Parent(s):
d6b3f33
fix cpu inference
Browse files- entrypoint.sh.template +1 -1
entrypoint.sh.template
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
mongod &
|
| 5 |
|
| 6 |
# Start the text-generation-inference process
|
| 7 |
-
text-generation-launcher --model-id ${MODEL_NAME} --num-shard 1 --port 8080 --trust-remote-code &
|
| 8 |
|
| 9 |
# Wait for text-generation-inference to start
|
| 10 |
curl --retry 60 --retry-delay 10 --retry-connrefused http://127.0.0.1:8080/health
|
|
|
|
| 4 |
mongod &
|
| 5 |
|
| 6 |
# Start the text-generation-inference process
|
| 7 |
+
text-generation-launcher --model-id ${MODEL_NAME} --num-shard 1 --port 8080 --trust-remote-code --dtype bfloat16 &
|
| 8 |
|
| 9 |
# Wait for text-generation-inference to start
|
| 10 |
curl --retry 60 --retry-delay 10 --retry-connrefused http://127.0.0.1:8080/health
|