Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention
Repository Index
140,194 visible repositories in the index
1–3 of 3 · Most stars
pytest fixture for benchmarking code
- python
- pytest
- benchmark
- benchmarking
Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
- cifar10
- deep-learning
- experimentation
- machine-learning