huggingface/candle
1
0
Fork 0
mirror of https://github.com/huggingface/candle.git synced 2025-06-16 18:48:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add flash attention (#241)

Browse Source 
* Add some flash-attn kernel, import the code for flash-attn v2 from Dao-AILab.

* More flash attn.

* Set up the flash attn parameters.

* Get things to compile locally.

* Move the flash attention files in a different directory.

* Build the static C library with nvcc.

* Add more flash attention.

* Update the build part.

* Better caching.

* Exclude flash attention from the default workspace.

* Put flash-attn behind a feature gate.

* Get the flash attn kernel to run.

* Move the flags to a more appropriate place.

* Enable flash attention in llama.

* Use flash attention in llama.
This commit is contained in:
Laurent Mazare
2023-07-26 07:48:10 +01:00
committed by GitHub
parent c97d51243c
commit d9f9c859af
22 changed files with 2699 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
candle-examples/examples/llama/main.rs
View File

@ -116,6 +116,9 @@ struct Args {
#[arg(long)]
v2: bool,
#[arg(long)]
use_flash_attn: bool,
}
fn main() -> Result<()> {
@ -124,7 +127,7 @@ fn main() -> Result<()> {
let args = Args::parse();
let device = candle_examples::device(args.cpu)?;
let config = Config::config_7b();
let config = Config::config_7b(args.use_flash_attn);
let cache = model::Cache::new(!args.no_kv_cache, &config, &device)?;
let dtype = if args.use_f32 { DType::F32 } else { DType::F16 };
let (llama, tokenizer_filename) = match args.npy {