Pannaga j
pannaga10
AI & ML interests
None yet
Recent Activity
new activity about 19 hours 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 4 days ago
google/gemma-4-31B-it:This model is so good, but the KV cache ruins it. new activity 6 days ago
google/gemma-4-E2B-it:How to best prompt for transcription results when sending audio input?Organizations
