Spaces:

TheLinconX
/

contextforge-demo

Sleeping

App Files Files Community

contextforge-demo / apohara_context_forge /quantization

30.2 kB

Ctrl+K

Ctrl+K

5 contributors

History: 2 commits

Pablo

fix: S-3 rotate_kv_quantization 4D indexing, S-13 speculative acceptance rate, Gradio real pipeline data

1652aca 1 day ago

__pycache__
fix: S-3 rotate_kv_quantization 4D indexing, S-13 speculative acceptance rate, Gradio real pipeline data 1 day ago
rotate_kv.py

14.1 kB
fix: S-3 rotate_kv_quantization 4D indexing, S-13 speculative acceptance rate, Gradio real pipeline data 1 day ago