Skip to content

Commit fa09172

Browse files
committed
comments #1 addressed
1 parent 8761356 commit fa09172

File tree

4 files changed

+50
-43
lines changed

4 files changed

+50
-43
lines changed

tutorials-and-examples/nvidia-nim/blueprints/README.md

Lines changed: 8 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -2,14 +2,7 @@
22

33
Here you will find the NVIDIA NIM Blueprints that can be provisioned to run on GKE. These are good for proof of concepts.
44

5-
1. [Generative Virtual Screening for Drug Discovery](https://build.nvidia.com/nvidia/generative-virtual-screening-for-drug-discovery) uses 3 NIMs.
6-
- AlphaFold2
7-
- MolMIM
8-
- DiffDock
9-
10-
You can follow the detailed steps [here](./drugdiscovery/README.md).
11-
12-
2. [Digital Human for Customer Service](https://build.nvidia.com/nvidia/digital-humans-for-customer-service)
5+
1. [Digital Human for Customer Service](https://build.nvidia.com/nvidia/digital-humans-for-customer-service)
136
- Audio2face-3D
147
- Audio2face-2D
158
- FastPitch-hifigan-tts
@@ -19,3 +12,10 @@ Here you will find the NVIDIA NIM Blueprints that can be provisioned to run on G
1912
- Parakeet-ctc-1.1b-asr
2013

2114
You can follow the detailed steps [here](./digitalhuman/README.md).
15+
16+
2. [Generative Virtual Screening for Drug Discovery](https://build.nvidia.com/nvidia/generative-virtual-screening-for-drug-discovery) uses 3 NIMs.
17+
- AlphaFold2
18+
- MolMIM
19+
- DiffDock
20+
21+
You can follow the detailed steps [here](./drugdiscovery/README.md).

tutorials-and-examples/nvidia-nim/blueprints/digitalhuman/README.md

Lines changed: 22 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -43,16 +43,15 @@ Deploying the digital human blueprint based on few NIMs on GKE.
4343

4444
```
4545

46-
2. **GKE Cluster creation**:
46+
2. **GKE Cluster and Node pool creation**:
4747

4848
```bash
4949
5050
gcloud container clusters create "${CLUSTER_NAME}" \
5151
--num-nodes="1" \
5252
--location="${ZONE}" \
5353
--machine-type="${NP_CPU_MACHTYPE}" \
54-
--gateway-api=standard \
55-
--addons=GcpFilestoreCsiDriver,HttpLoadBalancing
54+
--addons=GcpFilestoreCsiDriver
5655
5756
gcloud container node-pools create "${NP_NAME}" \
5857
--cluster="${CLUSTER_NAME}" \
@@ -67,15 +66,26 @@ Deploying the digital human blueprint based on few NIMs on GKE.
6766
6867
```
6968

70-
3. **Deploy NIMs:**
69+
3. **Get Cluster Credentials:**
7170

7271
```bash
7372
74-
gcloud container clusters get-credentials "${CLUSTER_NAME}" \
75-
--location="${ZONE}"
73+
gcloud container clusters get-credentials "${CLUSTER_NAME}" --location="${ZONE}"
7674
75+
```
76+
77+
4. **Set kubectl Alias (Optional):**
78+
79+
```bash
80+
7781
alias k=kubectl
7882
83+
```
84+
85+
5. **Create NGC API Key Secret:** Creates secrets for pulling images from NVIDIA NGC and pods that need the API key at startup.
86+
87+
```bash
88+
7989
k create secret docker-registry secret-nvcr \
8090
--docker-username=\$oauthtoken \
8191
--docker-password="${NGC_API_KEY}" \
@@ -84,6 +94,12 @@ Deploying the digital human blueprint based on few NIMs on GKE.
8494
k create secret generic ngc-api-key \
8595
--from-literal=NGC_API_KEY="${NGC_API_KEY}"
8696
97+
```
98+
99+
6. **Deploy NIMs:**
100+
101+
```bash
102+
87103
k apply -f digital-human-nimbp.yaml
88104
89105
```

tutorials-and-examples/nvidia-nim/blueprints/digitalhuman/digital-human-nimbp.yaml

Lines changed: 1 addition & 23 deletions
Original file line numberDiff line numberDiff line change
@@ -82,8 +82,7 @@ spec:
8282
spec:
8383
containers:
8484
- name: dighum-embedqa-e5v5
85-
# image: nvcr.io/nim/nvidia/nv-embedqa-e5-v5:1.0.1
86-
image: nvcr.io/nim/nvidia/nv-embedqa-e5-v5:latest
85+
image: nvcr.io/nim/nvidia/nv-embedqa-e5-v5:1.0.1
8786
ports:
8887
- containerPort: 8000
8988
resources:
@@ -420,25 +419,6 @@ spec:
420419
medium: Memory
421420
sizeLimit: 16Gi
422421

423-
# ---
424-
# apiVersion: v1
425-
# kind: Service
426-
# metadata:
427-
# name: dighum-audio2face-3d-lb
428-
# spec:
429-
# type: LoadBalancer
430-
# selector:
431-
# app: dighum-audio2face-3d
432-
# ports:
433-
# - protocol: TCP
434-
# name: http
435-
# port: 9000
436-
# targetPort: 9000
437-
# - protocol: TCP
438-
# name: grpc
439-
# port: 50051
440-
# targetPort: 50051
441-
442422
---
443423
apiVersion: apps/v1
444424
kind: Deployment
@@ -457,8 +437,6 @@ spec:
457437
containers:
458438
- name: dighum-maxine-audio2face-2d
459439
image: nvcr.io/nim/nvidia/maxine-audio2face-2d:latest
460-
# securityContext:
461-
# privileged: true
462440
ports:
463441
- containerPort: 8000
464442
name: http

tutorials-and-examples/nvidia-nim/blueprints/digitalhuman/https.md

Lines changed: 19 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -16,16 +16,29 @@ Deploying HTTPS endpoints for the digital human blueprint on GKE.
1616

1717
## Setup
1818

19-
1. **Environment setup**: You'll set up several environment variables to make the following steps easier and more flexible. These variables store important information like cluster names, machine types, and API keys. You need to update the variable values to match your needs and context.
19+
1. **Cluster update**: You'll need to update the cluster by enabling GKE Gateway controller and addon for HTTP LoadBalancing
20+
```bash
21+
22+
gcloud container clusters update "${CLUSTER_NAME}" \
23+
--location="${ZONE}" \
24+
--gateway-api=standard
25+
26+
gcloud container clusters update "${CLUSTER_NAME}" \
27+
--location="${ZONE}" \
28+
--update-addons=HttpLoadBalancing=ENABLED
29+
30+
```
31+
32+
2. **Environment setup**: You'll set up a couple of environment variables to make the following steps easier and more flexible. These variables store important information like cluster names, machine types, and API keys. You need to update the variable values to match your needs and context.
2033
2134
```bash
2235
23-
export NIMS="dighum-embedqa-e5v5 dighum-llama3-8b dighum-rerankqa-mistral4bv3"
36+
export NIMS="dighum-embedqa-e5v5 dighum-llama3-8b dighum-rerankqa-mistral4bv3 dighum-audio2face-3d dighum-fastpitch-tts dighum-maxine-audio2face-2d dighum-parakeet-asr-1-1b"
2437
export DOMAIN=<DOMAIN>
2538
2639
```
2740
28-
2. **Static IP Reservation**:
41+
3. **Static IP Reservation**:
2942
3043
```bash
3144
@@ -35,9 +48,9 @@ Deploying HTTPS endpoints for the digital human blueprint on GKE.
3548
3649
```
3750
38-
3. **DNS**: Configure the DNS subdomains for each NIM. Our sub-domains for this example should be in this format <NIM>.<DOMAIN> (e.g. llama3-8b.example.com).
51+
4. **DNS**: Configure the DNS subdomains for each NIM. Our sub-domains for this example should be in this format <NIM>.<DOMAIN> (e.g. llama3-8b.example.com).
3952
40-
4. **Creating the SSL Certs**
53+
5. **Creating the SSL Certs**
4154
4255
```bash
4356
@@ -47,7 +60,7 @@ Deploying HTTPS endpoints for the digital human blueprint on GKE.
4760
4861
```
4962
50-
5. **Create k8s service, gateway and http-route and healthcheck**
63+
6. **Create k8s service, gateway and http-route and healthcheck**
5164
5265
```bash
5366

0 commit comments

Comments
 (0)