Parallelise the CPU kernels for the conv ops. (#401)

* Parallelise the conv2d op.

* Tighter control on threading.

* Also parallelise conv1d.

* Add some safety comment.
This commit is contained in:
Laurent Mazare
2023-08-11 06:51:58 +02:00
committed by GitHub
parent a325c1aa50
commit e29c7809ec
5 changed files with 64 additions and 8 deletions

View File

@ -43,6 +43,7 @@ num_cpus = "1.15.0"
num-traits = "0.2.15"
rand = "0.8.5"
rand_distr = "0.4.3"
rayon = "1.7.0"
safetensors = "0.3.1"
serde = { version = "1.0.171", features = ["derive"] }
serde_json = "1.0.99"