Peter Kis's picture

Peter Kis

NePe

·

AI & ML interests

None yet

Recent Activity

new activity 7 days ago

nvidia/Llama-3_3-Nemotron-Super-49B-v1_5:variable_cache.py compatibility for v4.57.2 / python3.12

new activity 7 days ago

nvidia/Llama-3_3-Nemotron-Super-49B-v1_5:Since `transformers` v4.56.0` the dictionary `ALL_STATIC_CACHE_IMPLEMENTATIONS` replaced `NEED_SETUP_CACHE_CLASSES_MAPPING`

new activity 12 days ago

nvidia/Llama-3_3-Nemotron-Super-49B-v1_5:cannot import name 'NEED_SETUP_CACHE_CLASSES_MAPPING'

View all activity

Organizations

upvoted 2 papers over 1 year ago

Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence

Paper • 2404.05892 • Published Apr 8, 2024 • 40

GoldFinch: High Performance RWKV/Transformer Hybrid with Linear Pre-Fill and Extreme KV-Cache Compression

Paper • 2407.12077 • Published Jul 16, 2024 • 57