huggingface/candle
1
0
Fork 0
mirror of https://github.com/huggingface/candle.git synced 2025-06-21 20:22:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

Use HF Papers

Browse Source
This commit is contained in:
Quentin Gallouédec
2025-05-17 03:41:24 +00:00
parent 92106c8762
commit ffb8d63324
97 changed files with 113 additions and 113 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
candle-onnx/src/onnx.proto3
View File

@ -512,8 +512,8 @@ message TensorProto {
BFLOAT16 = 16;
// Non-IEEE floating-point format based on papers
// FP8 Formats for Deep Learning, https://arxiv.org/abs/2209.05433,
// 8-bit Numerical Formats For Deep Neural Networks, https://arxiv.org/pdf/2206.02915.pdf.
// FP8 Formats for Deep Learning, https://huggingface.co/papers/2209.05433,
// 8-bit Numerical Formats For Deep Neural Networks, https://huggingface.co/papers/2206.02915.
// Operators supported FP8 are Cast, CastLike, QuantizeLinear, DequantizeLinear.
// The computation usually happens inside a block quantize / dequantize
// fused by the runtime.