Laurent Mazare 140a8edf01 Merge pull request #14 from LaurentMazare/llama-opt ...

Cache the causal mask in llama.

2023-06-27 12:21:31 +01:00

.cargo

Add the topological sort for backprop.

2023-06-20 19:15:39 +01:00

.github/workflows

Remove the default features from the CI as cuda is not available.

2023-06-26 20:56:13 +01:00

candle-core

Cache the causal mask in llama.

2023-06-27 12:21:08 +01:00

candle-kernels

Fix two cuda bugs (matmul and where_cond).

2023-06-27 11:31:04 +01:00

.gitignore

Start sketching the llama example.

2023-06-25 13:51:20 +01:00

.pre-commit-config.yaml

Fixing tokenizers dep.

2023-06-22 12:25:58 +02:00

Cargo.toml

Refactor the hierarchy.

2023-06-27 11:57:27 +02:00

Makefile

Fix two cuda bugs (matmul and where_cond).

2023-06-27 11:31:04 +01:00

Description

No description provided

41 MiB

Languages

Rust 82%

Metal 5.9%

Cuda 4.2%

C++ 3%

Python 2.2%

Other 2.7%