mirror of
https://github.com/huggingface/candle.git
synced 2025-06-15 10:26:33 +00:00
d9904a3baf
* Start updating to cudarc 0.14. * Adapt a couple more things. * And a couple more fixes. * More tweaks. * And a couple more fixes. * Bump the major version number. * Proper module system for the cuda kernels. * Proper ptx loading. * Launch the sort kernel. * Custom op. * Start using the builder pattern. * More builder. * More builder. * Get candle-core to compile. * Get the tests to pass. * Get candle-nn to work too. * Support for custom cuda functions. * cudnn fixes. * Get flash attn to run. * Switch the crate versions to be alpha. * Bump the ug dependency.
25 lines
740 B
TOML
25 lines
740 B
TOML
[package]
|
|
name = "candle-flash-attn"
|
|
version = "0.9.0-alpha.1"
|
|
edition = "2021"
|
|
|
|
description = "Flash attention layer for the candle ML framework."
|
|
repository = "https://github.com/huggingface/candle"
|
|
keywords = ["blas", "tensor", "machine-learning"]
|
|
categories = ["science"]
|
|
license = "MIT OR Apache-2.0"
|
|
readme = "README.md"
|
|
|
|
[dependencies]
|
|
candle = { path = "../candle-core", features = ["cuda"], package = "candle-core", version = "0.9.0-alpha.1" }
|
|
half = { version = "2.3.1", features = ["num-traits"] }
|
|
|
|
[build-dependencies]
|
|
bindgen_cuda = "0.1.1"
|
|
anyhow = { version = "1", features = ["backtrace"] }
|
|
|
|
|
|
[dev-dependencies]
|
|
anyhow = { version = "1", features = ["backtrace"] }
|
|
candle-nn = { path = "../candle-nn", features = ["cuda"] }
|