Sign in Sign up
cargo

drama_llama

Local LLM inference behind an Anthropic-shaped API: llama.cpp and Metal-MoE backends, chat sessions with prefix caching, per-model tool-call dialects, and GBNF-constrained structured output.

cargo View on Cargo

Activity

Latest release
3w ago
Total releases
28
Cadence
~daily
Last 12 months
6

Details

License
unknown
First release
Apr 20, 2024
Releases
Version Released
0.9.0 minor
0.8.3 unknown
0.8.1 unknown
0.8.0 unknown
0.6.1 unknown
0.6.0 unknown
0.5.2 unknown
0.5.1 unknown
0.5.0 unknown
0.4.5 unknown
0.4.4 unknown
0.4.3 unknown
0.4.2 unknown
0.4.1 unknown
0.4.0 unknown
0.3.9 unknown
0.3.8 unknown
0.3.7 unknown
0.3.5 unknown
0.3.4 unknown
0.3.3 unknown
0.3.2 unknown
0.3.1 unknown
0.3.0 unknown
0.2.0 unknown
0.1.2 unknown
0.1.1 unknown
0.1.0 unknown