Krishna Teja Chitty-Venkata's picture

Building on HF

Krishna Teja Chitty-Venkata

krishnateja95

RedHatAI

·

https://krishnateja95.github.io/

AI & ML interests

LLM Optimization, Neural Architecture Search, Quantization, Pruning

Recent Activity

updated a model 1 day ago

inference-optimization/Llama-3.2-3B-Instruct_7_bits_mode_heuristic

published a model 1 day ago

inference-optimization/Llama-3.2-3B-Instruct_7_bits_mode_heuristic

updated a model 1 day ago

inference-optimization/Llama-3.2-3B-Instruct_7_bits_mode_noise

View all activity

Organizations

New activity in inference-optimization/sarvam-30b-NVFP4 4 days ago

Create README.md

#1 opened 5 days ago by

New activity in inference-optimization/sarvam-30b-FP8-Dynamic 4 days ago

Create README.md

#1 opened 5 days ago by

New activity in RedHatAI/granite-4.0-h-small-FP8-dynamic 3 months ago

Replace model with updated FP8 dynamic quantization

#1 opened 3 months ago by

New activity in RedHatAI/Qwen3-30B-A3B-FP8-block 5 months ago

Update README.md

#2 opened 5 months ago by

Create README.md

#1 opened 5 months ago by

New activity in krishnateja95/DeepseekVL2-4bit about 1 year ago

Is this the standard version or the tiny version?

#1 opened about 1 year ago by