Skip to content

Update prefix plugin guide to use vllm as default to be consistent #1078

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

Merged
merged 1 commit into from
Jun 27, 2025
Merged

Update prefix plugin guide to use vllm as default to be consistent #1078

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
7 changes: 3 additions & 4 deletions site-src/guides/epp-configuration/prefix-aware.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,6 @@ shows a detailed analysis on how to estimate this.
```
max_kv_tokens_per_server = (HBM_size - model_size)/ kv_size_per_token
lru_indexer_capacity_per_server = (max_kv_tokens_per_server * avg_chars_per_token)/prefix_indexer_hash_block_size
lru_indexer_capacity_total = max_num_servers * lru_indexer_capacity_per_server
Copy link
Contributor Author

Choose a reason for hiding this comment

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

We simplified the config and don't need this any more.

```

Let's take an example:
Expand All @@ -78,9 +77,9 @@ Use the following reference command to install an inferencepool with the prefix
cache plugin environment variable configurations:

```txt
$ helm install triton-llama3-8b-instruct \
--set inferencePool.modelServers.matchLabels.app=triton-llama3-8b-instruct \
--set inferencePool.modelServerType=triton-tensorrt-llm \
$ helm install vllm-llama3-8b-instruct \
--set inferencePool.modelServers.matchLabels.app=vllm-llama3-8b-instruct \
--set inferencePool.modelServerType=vllm \
--set provider.name=[none|gke] \
--set inferenceExtension.env.EXPERIMENTAL_USE_SCHEDULER_V2=true \
--set inferenceExtension.env.ENABLE_PREFIX_CACHE_SCHEDULING=true \
Expand Down