muhac/LLM in GitHub Actions
Run an LLM model on a vLLM server inside your CI pipeline.
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| model | Model name | yes | — |
| vllm_version | vLLM version tag | no | v0.17.0 |
| hf_token | Hugging Face access token | no | — |
| kv_cache_space | CPU KV cache size in GiB | no | — |
| max_model_len | Maximum sequence length for the model | no | — |
Outputs
| name | description |
|---|---|
| logs | vLLM server logs |