Giters
clebert
/
llama2.zig
Inference Llama 2 in pure Zig
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
40
Watchers:
4
Issues:
5
Forks:
3
clebert/llama2.zig Issues
Add support for multithreaded Matrix-vector multiplication
Closed
9 months ago
Add support for 8-bit Quantization
Updated
9 months ago
Fix chat output of llama2_7b_chat_uncensored model
Updated
9 months ago
Vector widths in matmul code and data dependencies
Closed
a year ago
Comments count
2
Running with -t 0 error
Closed
a year ago
Comments count
2