* bugfix: CUDA acceleration not working
CUDA not working after #2286.
Refactored the code to be more polish
* Update requirements.txt
Missing imports
Signed-off-by: fakezeta <fakezeta@gmail.com>
* Update requirements.txt
Signed-off-by: fakezeta <fakezeta@gmail.com>
---------
Signed-off-by: fakezeta <fakezeta@gmail.com>
update transformers
*Handle Temperature = 0 as greedy search
*Handle custom works as stop words
*Implement KV cache
*Phi 3 no more requires trust_remote_code: true