Expose optional intermediate hidden states / layer logits during generation (for reasoning metrics and model introspection)

Feature Request: Add `action_guard` Parameter for centralized validation of agent tool calls

Performance: Replace inefficient polling in server loop with event-driven shutdown and optimize Health check

KV-cache / long-context: smallest canonical repro boundary + metric (7-day receipts eval)

[Feature Request] MCP Server for AI-Powered Model Development

Get inference endpoint model settings via client

How to use prefix caching

ghcr.io/huggingface/text-generation-inference:3.3.5 doesn't exist

Infinite tool call loop: `HuggingFaceModel` and `text-generation-inference`

Endpoint failed to start due to ShardFailed on hugging face inference endpoint