Skip to content

Commit 36eacb9

Browse files
committed
docs: add phi3v to multimodal readme
1 parent d736895 commit 36eacb9

File tree

1 file changed

+6
-2
lines changed

1 file changed

+6
-2
lines changed

examples/multimodal/README.md

Lines changed: 6 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -54,6 +54,8 @@ cd $DYNAMO_HOME/examples/multimodal
5454
dynamo serve graphs.agg:Frontend -f ./configs/agg-llava.yaml
5555
# Serve a Qwen2 VL model:
5656
# dynamo serve graphs.agg:Frontend -f ./configs/agg-qwen.yaml
57+
# Serve a Phi3V model:
58+
# dynamo serve graphs.agg:Frontend -f ./configs/agg-phi3v.yaml
5759
```
5860

5961
### Client
@@ -87,7 +89,7 @@ curl http://localhost:8000/v1/chat/completions \
8789
}'
8890
```
8991

90-
If serving the example Qwen model, replace `"llava-hf/llava-1.5-7b-hf"` in the `"model"` field with `"Qwen/Qwen2-VL-7B-Instruct"`.
92+
If serving the example Qwen model, replace `"llava-hf/llava-1.5-7b-hf"` in the `"model"` field with `"Qwen/Qwen2-VL-7B-Instruct"`. If serving the example Phi3V model, replace `"llava-hf/llava-1.5-7b-hf"` in the `"model"` field with `"microsoft/Phi-3.5-vision-instruct"`.
9193

9294
You should see a response similar to this:
9395
```json
@@ -204,6 +206,8 @@ export DEPLOYMENT_NAME=multimodal-agg
204206
dynamo deploy $DYNAMO_TAG -n $DEPLOYMENT_NAME -f ./configs/agg-llava.yaml
205207
# For aggregated serving with Qwen2-VL:
206208
# dynamo deploy $DYNAMO_TAG -n $DEPLOYMENT_NAME -f ./configs/agg-qwen.yaml
209+
# For aggregated serving with Phi3V:
210+
# dynamo deploy $DYNAMO_TAG -n $DEPLOYMENT_NAME -f ./configs/agg-phi3v.yaml
207211
# For disaggregated serving:
208212
# export DEPLOYMENT_NAME=multimodal-disagg
209213
# dynamo deploy $DYNAMO_TAG -n $DEPLOYMENT_NAME -f ./configs/disagg.yaml
@@ -245,6 +249,6 @@ curl localhost:8000/v1/chat/completions \
245249
}'
246250
```
247251

248-
If serving the example Qwen model, replace `"llava-hf/llava-1.5-7b-hf"` in the `"model"` field with `"Qwen/Qwen2-VL-7B-Instruct"`.
252+
If serving the example Qwen model, replace `"llava-hf/llava-1.5-7b-hf"` in the `"model"` field with `"Qwen/Qwen2-VL-7B-Instruct"`. If serving the example Phi3V model, replace `"llava-hf/llava-1.5-7b-hf"` in the `"model"` field with `"microsoft/Phi-3.5-vision-instruct"`.
249253

250254
For more details on managing deployments, testing, and troubleshooting, please refer to the [Operator Deployment Guide](../../docs/guides/dynamo_deploy/operator_deployment.md).

0 commit comments

Comments
 (0)