Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

ChatQnA: Update chatqna-vllm-remote-inference #1224

Merged
merged 5 commits into from
Dec 4, 2024
Merged

ChatQnA: Update chatqna-vllm-remote-inference #1224

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
adbe650
ChatQnA: Updated imagePullPolicy of chatqna to Always instead of IfNo…
sgurunat Dec 4, 2024
7585256
ChatQnA: Updated model id to meta-llama-3.1-70b-instruct in chatqna-v…
sgurunat Dec 4, 2024
cbf657c
ChatQnA: Updated nginx properties to have smooth streaming experience…
sgurunat Dec 4, 2024
da229fa
ChatQnA: Added MODEL_ID env variable for chatqna-ui in chatqna-vllm-r…
sgurunat Dec 4, 2024
3a344ce
Merge branch 'main' into chatqna-gaudi
sgurunat Dec 4, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 11 additions & 4 deletions ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm-remote-inference.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,8 +76,8 @@ data:
no_proxy: ""
LOGFLAG: ""
vLLM_ENDPOINT: "insert-your-remote-vllm-inference-endpoint"
LLM_MODEL: "meta-llama/Meta-Llama-3.1-8B-Instruct"
MODEL_ID: "meta-llama/Meta-Llama-3.1-8B-Instruct"
LLM_MODEL: "meta-llama/Meta-Llama-3.1-70B-Instruct"
MODEL_ID: "meta-llama/Meta-Llama-3.1-70B-Instruct"
CLIENTID: ""
CLIENT_SECRET: ""
TOKEN_URL: ""
Expand Down Expand Up @@ -174,6 +174,10 @@ data:
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
proxy_buffering off;
proxy_cache off;
proxy_request_buffering off;
gzip off;
}

location /v1/dataprep {
Expand Down Expand Up @@ -459,6 +463,9 @@ spec:
{}
containers:
- name: chatqna-ui
env:
- name: MODEL_ID
value: "meta-llama/Meta-Llama-3.1-70B-Instruct"
securityContext:
{}
image: "opea/chatqna-ui:latest"
Expand Down Expand Up @@ -981,7 +988,7 @@ spec:
- name: EMBEDDING_SERVICE_HOST_IP
value: chatqna-embedding-usvc
- name: MODEL_ID
value: "meta-llama/Meta-Llama-3.1-8B-Instruct"
value: "meta-llama/Meta-Llama-3.1-70B-Instruct"
securityContext:
allowPrivilegeEscalation: false
capabilities:
Expand All @@ -993,7 +1000,7 @@ spec:
seccompProfile:
type: RuntimeDefault
image: "opea/chatqna-wrapper:latest"
imagePullPolicy: IfNotPresent
imagePullPolicy: Always
volumeMounts:
- mountPath: /tmp
name: tmp
Expand Down
Loading