atomr-infer-runtime-vllm
cargovLLM runner for atomr-infer. Hosts local LLMs via PyO3-bound AsyncLLMEngine + token-streaming. Includes Gemma 4 auto-provisioning helpers under the `gemma-default` feature.
Audits
No audits for this package yet.
vLLM runner for atomr-infer. Hosts local LLMs via PyO3-bound AsyncLLMEngine + token-streaming. Includes Gemma 4 auto-provisioning helpers under the `gemma-default` feature.