Skip to content

Commit 986acc7

Browse files
committed
refactor: Makefile, update docs, revert epp build back to go 1.24
- split Makefile 1. tools: include install tools, check tools, download dependency(gcc etc) and tokenizer. these will be download into "bin" folder than global path 2. cluster: include k8s and ocp 3. kind - revert Go version back to 1.24 in Dockerfile.epp - rename "openshift-base" to "kubernetes-base" to be clear for purpose - uplift Go lint version to 2.1.6 to align with the same one set in Github Action - rename make targets for better visibility, deprcating old ones - add variables to be exported with python path, so CGO for kv-cache-manager can find python header file to compile. Signed-off-by: Wen Zhou <wenzhou@redhat.com>
1 parent ef052e8 commit 986acc7

17 files changed

+402
-314
lines changed

DEVELOPMENT.md

Lines changed: 6 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -140,7 +140,7 @@ Operators, etc.) to support the namespace-level development environments:
140140
Install Gateway API + GIE CRDs:
141141

142142
```bash
143-
kubectl apply -f https://github.com/kubernetes-sigs/gateway-api/releases/download/v1.3.0/standard-install.yaml
143+
kubectl apply -f https://github.com/kubernetes-sigs/gateway-api/releases/download/v1.4.0/standard-install.yaml
144144
kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/releases/latest/download/manifests.yaml
145145
```
146146

@@ -229,13 +229,16 @@ curl -s -w '\n' http://localhost:8080/v1/completions -H 'Content-Type: applicati
229229

230230
**1. Setting the EPP image and tag:**
231231

232-
You can optionally set a custom EPP image (otherwise, the default will be used):
232+
You can optionally set a custom EPP image and tag (otherwise, defaults will be used):
233233

234234
```bash
235+
export IMAGE_REGISTRY="<YOUR_REGISTRY>"
235236
export EPP_TAG="<YOUR_TAG>"
236-
export EPP_IMAGE="<YOUR_REGISTRY>/<YOUR_IMAGE>"
237237
```
238238

239+
> [!NOTE]
240+
> The full image reference will be constructed as `${EPP_IMAGE}:${EPP_TAG}`, where `EPP_IMAGE` defaults to `${IMAGE_REGISTRY}/llm-d-inference-scheduler`. For example, with `IMAGE_REGISTRY=quay.io/<my-id>` and `EPP_TAG=v1.0.0`, the final image will be `quay.io/<my-id>/llm-d-inference-scheduler:v1.0.0`.
241+
239242
**2. Setting the vLLM replicas:**
240243

241244
You can optionally set the vllm replicas:

Dockerfile.epp

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
## Minimal runtime Dockerfile (microdnf-only, no torch, wrapper in site-packages)
2-
# Build Stage: using Go 1.25 image
3-
FROM quay.io/projectquay/golang:1.25 AS builder
2+
# Build Stage: using Go 1.24 image
3+
FROM quay.io/projectquay/golang:1.24 AS builder
44

55
ARG TARGETOS
66
ARG TARGETARCH

0 commit comments

Comments
 (0)