Limits and compatibility

These are current 0.2.0 product boundaries, not future commitments.

HTTP and media

• chat completions support n = 1;
• embedding output supports encoding_format = "float";
• one image may be attached to a generation request;
• supported image containers are PNG, JPEG, WebP, and GIF;
• decoded application image input is limited to 20 MiB;
• the default HTTP body limit is 29,360,128 bytes;
• default request timeout is 300 seconds;
• default HTTP concurrency is 16 requests;
• CORS is disabled until exact origins are configured.

Web dashboard

• the dashboard is opt-in;
• it is restricted to loopback;
• its local session lasts eight hours;
• the OpenAI bearer token cannot authorize dashboard administration.

Models

• compatibility is determined from configuration, tokenizer, tensor schema, shapes, quantization, and backend capabilities;
• a family or repository name is not a compatibility guarantee;
• Metal and CUDA have different admitted checkpoint coverage;
• a forced load bypasses memory-fit policy, not structural validation;
• model load cancellation waits for a future safe backend interruption boundary.

libmir stability

libmir is pre-1.0. Pin 0.2.0, review release notes before upgrading, and prefer the top-level facade over internal workspace crates.