huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 20:04:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fmt.

Browse Source
This commit is contained in:
Nicolas Patry 2023-09-27 09:05:39 +00:00
parent 086d62dbe3
commit e93705e272
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
launcher/src/main.rs
View File

@ -36,7 +36,10 @@ enum Quantization {
Gptq, Gptq,
/// Bitsandbytes 8bit. Can be applied on any model, will cut the memory requirement in half, /// Bitsandbytes 8bit. Can be applied on any model, will cut the memory requirement in half,
/// but it is known that the model will be much slower to run than the native f16. /// but it is known that the model will be much slower to run than the native f16.
#[deprecated(since="1.1.0", note="Use `eetq` instead, which provides better latencies overall and is drop-in in most cases")] #[deprecated(
since = "1.1.0",
note = "Use `eetq` instead, which provides better latencies overall and is drop-in in most cases"
)]
Bitsandbytes, Bitsandbytes,
/// Bitsandbytes 4bit. Can be applied on any model, will cut the memory requirement by 4x, /// Bitsandbytes 4bit. Can be applied on any model, will cut the memory requirement by 4x,
/// but it is known that the model will be much slower to run than the native f16. /// but it is known that the model will be much slower to run than the native f16.