Pannaga j's picture

Pannaga j

pannaga10

·

AI & ML interests

None yet

Recent Activity

new activity 5 days ago

google/gemma-4-31B-it:Gemma4 is super slow on vllm docker , max to max 15 token per second only (4 X L4 GPU)

new activity 9 days ago

google/gemma-4-31B-it:This model is so good, but the KV cache ruins it.

new activity 11 days ago

google/gemma-4-E2B-it:How to best prompt for transcription results when sending audio input?

View all activity

Organizations

pannaga10 's datasets

None public yet