LLM in a flash: Efficient Large Language Model Inference with Limited Memory
Paper
•
2312.11514
•
Published
•
259
Winthrop Gillis
wgillis
·
AI & ML interests
Reinforcement learning
Probabilistic modeling
Recent Activity
liked
a model
about 1 month ago
hexgrad/Kokoro-82M
liked
a model
10 months ago
meta-llama/Meta-Llama-3-8B
liked
a model
11 months ago
google/recurrentgemma-2b-it
Organizations
None yet