Search results

migrate to uv

Status: Open.

#14 In slashml/amd_inference;

· eff-kay opened on Jan 17, 2025

Implement paged attention

Status: Open.

#13 In slashml/amd_inference;

· eff-kay opened on Oct 7, 2024

how to run this on G4ad instances, it supports 5.2

Status: Open.

#11 In slashml/amd_inference;

· eff-kay opened on Oct 3, 2024

update the readme to reflect OS limitations, i..e windows, mac, linux

Status: Open.

#10 In slashml/amd_inference;

· eff-kay opened on Oct 3, 2024

add CD tests

Status: Open.

#9 In slashml/amd_inference;

· eff-kay opened on Oct 3, 2024

Make a list of drivers supported and images supported

Status: Open.

#8 In slashml/amd_inference;

· eff-kay opened on Oct 3, 2024

Add batching of inference, see how we can do that with pytorch.

Status: Open.

#7 In slashml/amd_inference;

· eff-kay opened on Oct 3, 2024

make the docker images smaller.

Status: Open.

#6 In slashml/amd_inference;

· eff-kay opened on Oct 3, 2024

test with ubuntu 24

Status: Open.

#5 In slashml/amd_inference;

· eff-kay opened on Oct 3, 2024

update readme to run from terminal without docker files.

Status: Open.

#4 In slashml/amd_inference;

· eff-kay opened on Oct 3, 2024

Docker image fails to build: "List directory /var/lib/apt/lists/partial is missing."

Status: Open.

#2 In slashml/amd_inference;

· CaseyLabs opened on Oct 3, 2024