phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-10 13:28:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

guidellm, runs, charts

Browse source 
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-09-23 16:10:23 -07:00
parent 8d8261961e
commit 4dfb379a42
14 changed files with 1436 additions and 526 deletions
Download patch file Download diff file Expand all files Collapse all files

6
benchmarking/k8s-benchmark/stack-k8s.yaml.template
View file

@ -58,14 +58,14 @@ spec:
value: "/etc/config/stack_run_config.yaml"
- name: LLAMA_STACK_WORKERS
value: "${LLAMA_STACK_WORKERS}"
command: ["uvicorn", "llama_stack.core.server.server:create_app", "--host", "0.0.0.0", "--port", "8323", "--workers", "$LLAMA_STACK_WORKERS", "--factory"]
command: ["uvicorn", "llama_stack.core.server.server:create_app", "--host", "0.0.0.0", "--port", "8323", "--workers", "$(LLAMA_STACK_WORKERS)", "--factory"]
ports:
- containerPort: 8323
resources:
requests:
cpu: "${LLAMA_STACK_WORKERS}"
cpu: "4"
limits:
cpu: "${LLAMA_STACK_WORKERS}"
cpu: "4"
volumeMounts:
- name: llama-storage
mountPath: /root/.llama