NanoGPT (124M) in 90 seconds
Repository Index
104,105 visible repositories in the index
1–5 of 5 · Most stars
Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention
Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)
- vae
- benchmarking
- beta-vae
- comparison
Speedrun for pretraining without backpropagation
Benchmark harness and data: QEMU emulation vs native Buildx nodes for multi-arch container builds.