huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-19 22:02:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add NVIDIA A40 to known cards (#2941)

Browse Source 
feat: add NVIDIA A40 to known cards
This commit is contained in:
Nikolai Kolodziej 2025-01-23 14:19:21 +01:00 committed by GitHub
parent 6ab02931cf
commit 4e172028aa
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
launcher/src/main.rs
View File

@ -1632,6 +1632,7 @@ enum Gpu {
L40, L40,
L40S, L40S,
A10G, A10G,
A40,
H100, H100,
A100, A100,
Unknown(String), Unknown(String),
@ -1652,6 +1653,7 @@ impl From<&str> for Gpu {
"nvidia-l40" => Gpu::L40, "nvidia-l40" => Gpu::L40,
"nvidia-l40s" => Gpu::L40S, "nvidia-l40s" => Gpu::L40S,
"nvidia-a10g" => Gpu::A10G, "nvidia-a10g" => Gpu::A10G,
"nvidia-a40" => Gpu::A40,
"nvidia-h100-80gb-hbm3" => Gpu::H100, "nvidia-h100-80gb-hbm3" => Gpu::H100,
"nvidia-h100-nvl" => Gpu::H100, "nvidia-h100-nvl" => Gpu::H100,
"nvidia-h100" => Gpu::H100, "nvidia-h100" => Gpu::H100,
@ -1673,6 +1675,7 @@ impl std::fmt::Display for Gpu {
Gpu::L40 => write!(f, "nvida-l40"), Gpu::L40 => write!(f, "nvida-l40"),
Gpu::L40S => write!(f, "nvida-l40s"), Gpu::L40S => write!(f, "nvida-l40s"),
Gpu::A10G => write!(f, "nvidia-a10g"), Gpu::A10G => write!(f, "nvidia-a10g"),
Gpu::A40 => write!(f, "nvidia-a40"),
Gpu::H100 => write!(f, "nvidia-h100-80fb-hbm3"), Gpu::H100 => write!(f, "nvidia-h100-80fb-hbm3"),
Gpu::A100 => write!(f, "nvida-a100-sxm4-80gb"), Gpu::A100 => write!(f, "nvida-a100-sxm4-80gb"),
Gpu::Unknown(card) => write!(f, "{}", card), Gpu::Unknown(card) => write!(f, "{}", card),
@ -1696,6 +1699,9 @@ impl ComputeType {
Gpu::L40S => Some(363 * 10u64.pow(12)), Gpu::L40S => Some(363 * 10u64.pow(12)),
// https://www.nvidia.com/en-us/data-center/products/a10-gpu/ // https://www.nvidia.com/en-us/data-center/products/a10-gpu/
Gpu::A10G => Some(125 * 10u64.pow(12)), Gpu::A10G => Some(125 * 10u64.pow(12)),
// https://www.nvidia.com/en-us/data-center/a40/
// https://images.nvidia.com/content/Solutions/data-center/a40/nvidia-a40-datasheet.pdf
Gpu::A40 => Some(149 * 10u64.pow(12)),
// https://www.nvidia.com/en-us/data-center/h100/ // https://www.nvidia.com/en-us/data-center/h100/
// https://www.techpowerup.com/gpu-specs/docs/nvidia-gh100-architecture.pdf // https://www.techpowerup.com/gpu-specs/docs/nvidia-gh100-architecture.pdf
Gpu::H100 => Some(900 * 10u64.pow(12)), Gpu::H100 => Some(900 * 10u64.pow(12)),