huggingface/candle
1
0
Fork 0
mirror of https://github.com/huggingface/candle.git synced 2025-06-21 12:20:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

working bfloat matmul

Browse Source
This commit is contained in:
Ivar Flakstad
2024-03-18 14:38:40 +01:00
parent 0c09d10f32
commit c974dee369
6 changed files with 32 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
candle-core/benches/benchmarks/matmul.rs
View File

@ -13,11 +13,11 @@ fn run_bench(c: &mut Criterion, device: &Device) {
let n = 2048;
let k = 2048;
let dtype = DType::F32;
let dtype = DType::BF16;
let lhs = Tensor::zeros((b, m, k), dtype, device).unwrap();
let rhs = Tensor::zeros((b, n, k), dtype, device).unwrap();
let flops = b * m * n * k;
let flops = b * m * n * k * dtype.size_in_bytes();
let mut group = c.benchmark_group(device.bench_name("matmul"));
group.throughput(Throughput::Bytes(flops as u64));