Chillee / lit-llama
Simple (fast) transformer inference in PyTorch with torch.compile + lit-llama code
☆10Updated last year
Alternatives and similar repositories for lit-llama:
Users that are interested in lit-llama are comparing it to the libraries listed below
- An implementation of the Llama architecture, to instruct and delight☆21Updated 3 months ago
- Experiment of using Tangent to autodiff triton☆78Updated last year
- See https://github.com/cuda-mode/triton-index/ instead!☆11Updated 11 months ago
- ☆20Updated last year
- ☆21Updated 5 months ago
- ☆19Updated 3 weeks ago
- ☆51Updated 11 months ago
- ☆53Updated last year
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32Updated 10 months ago
- Automatically take good care of your preemptible TPUs☆36Updated last year
- Latent Diffusion Language Models☆68Updated last year
- A place to store reusable transformer components of my own creation or found on the interwebs☆49Updated this week
- Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.☆30Updated 4 months ago
- ☆20Updated 11 months ago
- Blog post☆17Updated last year
- ☆77Updated 9 months ago
- ☆33Updated 7 months ago
- RWKV model implementation☆37Updated last year
- ☆52Updated 6 months ago
- Triton Implementation of HyperAttention Algorithm☆47Updated last year
- Using FlexAttention to compute attention with different masking patterns☆43Updated 6 months ago
- LayerNorm(SmallInit(Embedding)) in a Transformer to improve convergence☆60Updated 3 years ago
- ☆17Updated 7 months ago
- gzip Predicts Data-dependent Scaling Laws☆34Updated 10 months ago
- Experiments for efforts to train a new and improved t5☆77Updated last year
- ☆27Updated last year
- Minimal but scalable implementation of large language models in JAX☆34Updated 5 months ago
- ☆49Updated last year
- ☆18Updated last year
- Code for the paper "Function-Space Learning Rates"☆18Updated this week