@codecai/web-llm
MITCodec-aware browser LLM runtime. Wraps the patched wdunn001/web-llm fork (`stream_format: "raw"`) so a local WebGPU engine emits raw token-ID CodecFrames byte-identically to what vLLM / sglang / llama.cpp produce over HTTP. Host does no tokenize/detokeniz
100
Security score
0 known advisories in v0.5.0
Weekly downloads
10
Unpacked size
22.3 kB
Dependencies
3
Last publish
3 months ago
Security advisories
No known vulnerabilities affect v0.5.0.
Downloads — last 30 days
54 total▼ 28.6% vs prior week
Jul 11Aug 9