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

Update HuggingFace DLC for TGI URI to 2.3 (latest) #852

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Update HuggingFace DLC for TGI URI to 2.3 (latest) #852

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4994c11
Update HuggingFace DLC for TGI URI to 2.3 (latest)
alvarobartt Oct 18, 2024
bceb12a
Update `mountPath` to point to `/tmp` instead of `/data`
alvarobartt Jan 7, 2025
1cce0af
Apply suggestions from code review
alvarobartt Jan 8, 2025
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
11 changes: 7 additions & 4 deletions modules/inference-service/main.tf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,7 +89,7 @@ resource "kubernetes_deployment" "inference_deployment" {
}
}
container {
image = "us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-generation-inference-cu121.2-2.ubuntu2204.py310"
image = "us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-generation-inference-cu124.2-3.ubuntu2204.py311"
name = "mistral-7b-instruct"

port {
Expand Down Expand Up @@ -132,8 +132,11 @@ resource "kubernetes_deployment" "inference_deployment" {
}

volume_mount {
mount_path = "/data"
name = "data"
# mount_path is set to /tmp as it's the path where the HF_HOME environment
# variable points to i.e. where the downloaded model from the Hugging Face
# Hub will be stored
mount_path = "/tmp"
alvarobartt marked this conversation as resolved.
Show resolved Hide resolved
name = "tmp"
}

volume_mount {
Expand Down Expand Up @@ -166,7 +169,7 @@ resource "kubernetes_deployment" "inference_deployment" {
}

volume {
name = "data"
name = "tmp"
empty_dir {}
}

Expand Down
6 changes: 3 additions & 3 deletions tutorials-and-examples/genAI-LLM/deploying-mistral-7b-instruct-L4gpus/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,7 +104,7 @@ Pod Template:
Labels: app=mistral-7b
Containers:
mistral-7b:
Image: us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-generation-inference-cu121.2-2.ubuntu2204.py310
Image: us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-generation-inference-cu124.2-3.ubuntu2204.py311
Port: 8080/TCP
Host Port: 0/TCP
Limits:
Expand All @@ -115,14 +115,14 @@ Pod Template:
PORT: 8080
QUANTIZE: bitsandbytes-nf4
Mounts:
/data from data (rw)
/tmp from tmp (rw)
/dev/shm from dshm (rw)
Volumes:
dshm:
Type: EmptyDir (a temporary directory that shares a pod's lifetime)
Medium: Memory
SizeLimit: <unset>
data:
tmp:
Type: HostPath (bare host directory volume)
Path: /mnt/stateful_partition/kube-ephemeral-ssd/mistral-data
HostPathType:
Expand Down
8 changes: 4 additions & 4 deletions tutorials-and-examples/genAI-LLM/deploying-mistral-7b-instruct-L4gpus/mistral-7b.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ spec:
spec:
containers:
- name: mistral-7b
image: us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-generation-inference-cu121.2-2.ubuntu2204.py310
image: us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-generation-inference-cu124.2-3.ubuntu2204.py311
resources:
limits:
nvidia.com/gpu: 1
Expand All @@ -47,13 +47,13 @@ spec:
volumeMounts:
- mountPath: /dev/shm
name: dshm
- mountPath: /data
name: data
- mountPath: /tmp
name: tmp
volumes:
- name: dshm
emptyDir:
medium: Memory
- name: data
- name: tmp
hostPath:
path: /mnt/stateful_partition/kube-ephemeral-ssd/mistral-data
---
Expand Down
6 changes: 3 additions & 3 deletions tutorials-and-examples/genAI-LLM/deploying-mixtral-8x7b-instruct-L4-gpus/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,7 +127,7 @@ Pod Template:
Labels: app=mixtral8x7b
Containers:
mixtral8x7b:
Image: us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-generation-inference-cu121.2-2.ubuntu2204.py310
Image: us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-generation-inference-cu124.2-3.ubuntu2204.py311
Port: 8080/TCP
Host Port: 0/TCP
Limits:
Expand All @@ -144,14 +144,14 @@ Pod Template:
NUM_SHARD: 2
PORT: 8080
Mounts:
/data from ephemeral-volume (rw)
/tmp from ephemeral-volume (rw)
/dev/shm from dshm (rw)
Volumes:
dshm:
Type: EmptyDir (a temporary directory that shares a pod's lifetime)
Medium: Memory
SizeLimit: <unset>
data:
tmp:
Type: HostPath (bare host directory volume)
Path: /mnt/stateful_partition/kube-ephemeral-ssd/mixtral-data
HostPathType:
Expand Down
6 changes: 3 additions & 3 deletions tutorials-and-examples/genAI-LLM/deploying-mixtral-8x7b-instruct-L4-gpus/mixtral-8x7b.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ spec:
cloud.google.com/gke-accelerator: "nvidia-l4"
containers:
- name: mixtral8x7b
image: us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-generation-inference-cu121.2-2.ubuntu2204.py310
image: us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-generation-inference-cu124.2-3.ubuntu2204.py311
ports:
- name: server-port
containerPort: 8080
Expand All @@ -53,15 +53,15 @@ spec:
memory: "42Gi"
nvidia.com/gpu: "2"
volumeMounts:
- mountPath: /data
- mountPath: /tmp
name: ephemeral-volume
- mountPath: /dev/shm
name: dshm
volumes:
- name: dshm
emptyDir:
medium: Memory
- name: data
- name: tmp
hostPath:
path: /mnt/stateful_partition/kube-ephemeral-ssd/mixtral-data
- name: ephemeral-volume
Expand Down
8 changes: 4 additions & 4 deletions tutorials-and-examples/genAI-LLM/serving-llama2-70b-on-l4-gpus/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,7 +76,7 @@ spec:
spec:
containers:
- name: llama-2-70b
image: us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-generation-inference-cu121.2-2.ubuntu2204.py310
image: us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-generation-inference-cu124.2-3.ubuntu2204.py311
resources:
limits:
nvidia.com/gpu: 2
Expand All @@ -97,13 +97,13 @@ spec:
volumeMounts:
- mountPath: /dev/shm
name: dshm
- mountPath: /data
name: data
- mountPath: /tmp
name: tmp
volumes:
- name: dshm
emptyDir:
medium: Memory
- name: data
- name: tmp
hostPath:
path: /mnt/stateful_partition/kube-ephemeral-ssd/llama-data
nodeSelector:
Expand Down
8 changes: 4 additions & 4 deletions ...rials-and-examples/genAI-LLM/serving-llama2-70b-on-l4-gpus/text-generation-interface.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ spec:
spec:
containers:
- name: llama-2-70b
image: us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-generation-inference-cu121.2-2.ubuntu2204.py310
image: us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-generation-inference-cu124.2-3.ubuntu2204.py311
resources:
limits:
nvidia.com/gpu: 2
Expand All @@ -49,13 +49,13 @@ spec:
volumeMounts:
- mountPath: /dev/shm
name: dshm
- mountPath: /data
name: data
- mountPath: /tmp
name: tmp
volumes:
- name: dshm
emptyDir:
medium: Memory
- name: data
- name: tmp
hostPath:
path: /mnt/stateful_partition/kube-ephemeral-ssd/llama-data
nodeSelector:
Expand Down
Loading