managarten/packages/local-llm/src
Till JS 4fd5ff3199 feat(local-llm): add Gemma 2 + allow HF/MLC hosts in CSP
WebLLM was blocked by connect-src — model config and weight shards live
on huggingface.co (+ cdn-lfs.* for LFS), and the WebGPU model_lib WASM
comes from raw.githubusercontent.com (binary-mlc-llm-libs). Also wires
Gemma 2 2B/9B into the model registry so /llm-test picks them up.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-08 18:00:57 +02:00
..
cache.ts fix(local-llm): wrap @mlc-ai/web-llm in dynamic import for Docker builds 2026-04-02 12:22:20 +02:00
engine.ts feat(local-llm): add client-side LLM inference package with WebLLM 2026-04-02 01:53:54 +02:00
generate.ts feat(local-llm): add generate utilities and reactive Svelte status 2026-04-02 11:57:50 +02:00
index.ts fix(local-llm): wrap @mlc-ai/web-llm in dynamic import for Docker builds 2026-04-02 12:22:20 +02:00
models.ts feat(local-llm): add Gemma 2 + allow HF/MLC hosts in CSP 2026-04-08 18:00:57 +02:00
status.svelte.ts feat(local-llm): add generate utilities and reactive Svelte status 2026-04-02 11:57:50 +02:00
svelte.svelte.ts feat: rename ManaCore to Mana across entire codebase 2026-04-05 20:00:13 +02:00
types.ts feat: rename ManaCore to Mana across entire codebase 2026-04-05 20:00:13 +02:00