Does ctransformers boost the inference speed in llm inference? #202

Open
opened 2024-02-15 08:26:33 -05:00 by pradeepdev-1995 · 0 comments
pradeepdev-1995 commented 2024-02-15 08:26:33 -05:00 (Migrated from github.com)

I have converted my finetuned hugging face model to .gguf format and triggered the inference with ctransformers.
I am using a CUDA GPU machine.
But i did not observe any kind of inference speed improvement after the inference by ctransformers. Observing the same latency in transformer based infernce and ctransformer based inference.

I have converted my finetuned hugging face model to .gguf format and triggered the inference with ctransformers. I am using a CUDA GPU machine. But i did not observe any kind of inference speed improvement after the inference by ctransformers. Observing the same latency in transformer based infernce and ctransformer based inference.
Sign in to join this conversation.
No labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
marella/ctransformers#202
No description provided.