Skip to content

docs: update tokenization pool configuration #230

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
github-actions merged 1 commit into from
Dec 26, 2025
Merged

docs: update tokenization pool configuration #230

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
3 changes: 3 additions & 0 deletions docs/configuration.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,6 +60,7 @@ Here's a complete configuration example with all options:
"metricsLoggingInterval": "1m0s"
},
"tokenizersPoolConfig": {
"modelName": "namespace/model-name",
"workersCount": 8,
"minPrefixOverlapRatio": 0.85,
"hf": {
Expand Down Expand Up @@ -217,6 +218,7 @@ Configures the tokenization worker pool and cache utilization strategy.

```json
{
"modelName": "namespace/model-name",
"workersCount": 5,
"minPrefixOverlapRatio": 0.8,
"hf": {
Expand All @@ -236,6 +238,7 @@ Configures the tokenization worker pool and cache utilization strategy.

| Field | Type | Description | Default |
|-------------------------|------------------------|-------------------------------------------------------------|---------|
| `modelName` | `string` | Base model name for the tokenizer. | |
| `workersCount` | `integer` | Number of tokenization worker goroutines | `5` |
| `minPrefixOverlapRatio` | `float64` | Minimum overlap ratio to use cached prefix tokens (0.0-1.0) | `0.8` |
| `hf` | `HFTokenizerConfig` | HuggingFace tokenizer config | |
Expand Down
Loading