Skip to content

Add a kvcache example deployment #297

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add a kvcache example deployment #297

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
30 changes: 30 additions & 0 deletions quickstart/examples/kvcache/kvcache.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,30 @@
sampleApplication:
baseConfigMapRefName: basic-gpu-with-nixl-and-redis-lookup-preset
model:
modelArtifactURI: hf://meta-llama/Llama-3.2-3B-Instruct
modelName: "meta-llama/Llama-3.2-3B-Instruct"
redis:
enabled: true
modelservice:
epp:
defaultEnvVarsOverride:
- name: ENABLE_KVCACHE_AWARE_SCORER
value: "true"
- name: ENABLE_PREFIX_AWARE_SCORER
value: "false"
- name: ENABLE_LOAD_AWARE_SCORER
value: "true"
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

More of a question then a comment, but do we want both load scorer and KVCache aware scorer or just 1?

- name: ENABLE_SESSION_AWARE_SCORER
value: "false"
- name: PD_ENABLED
value: "false"
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Dont we need P/D Enabled for KVCache Aware routing?

- name: PD_PROMPT_LEN_THRESHOLD
value: "10"
- name: PREFILL_ENABLE_KVCACHE_AWARE_SCORER
value: "false"
- name: PREFILL_ENABLE_LOAD_AWARE_SCORER
value: "false"
- name: PREFILL_ENABLE_PREFIX_AWARE_SCORER
value: "false"
- name: PREFILL_ENABLE_SESSION_AWARE_SCORER
value: "false"
34 changes: 34 additions & 0 deletions quickstart/examples/kvcache/slim/kvcache-slim.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
sampleApplication:
baseConfigMapRefName: basic-gpu-with-nixl-and-redis-lookup-preset
model:
modelArtifactURI: hf://Qwen/Qwen3-0.6B
modelName: "Qwen/Qwen3-0.6B"
prefill:
replicas: 0
decode:
replicas: 1
redis:
enabled: true
modelservice:
epp:
defaultEnvVarsOverride:
- name: ENABLE_KVCACHE_AWARE_SCORER
value: "true"
- name: ENABLE_PREFIX_AWARE_SCORER
value: "false"
- name: ENABLE_LOAD_AWARE_SCORER
value: "true"
- name: ENABLE_SESSION_AWARE_SCORER
value: "false"
- name: PD_ENABLED
value: "false"
- name: PD_PROMPT_LEN_THRESHOLD
value: "10"
- name: PREFILL_ENABLE_KVCACHE_AWARE_SCORER
value: "false"
- name: PREFILL_ENABLE_LOAD_AWARE_SCORER
value: "false"
- name: PREFILL_ENABLE_PREFIX_AWARE_SCORER
value: "false"
- name: PREFILL_ENABLE_SESSION_AWARE_SCORER
value: "false"
Loading