huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 04:14:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix typos in launcher help.

Browse Source
This commit is contained in:
Nicolas Patry 2024-01-23 15:31:13 +01:00
parent b91921f276
commit c0ade6bba2
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/basic_tutorials/launcher.md
View File

@ -62,7 +62,7 @@ Options:
Possible values: Possible values:
- awq: 4 bit quantization. Requires a specific AWQ quantized model: https://hf.co/models?search=awq. Should replace GPTQ models wherever possible because of the better latency - awq: 4 bit quantization. Requires a specific AWQ quantized model: https://hf.co/models?search=awq. Should replace GPTQ models wherever possible because of the better latency
- eetq: 8 bit quantization, doesn't require specific model. Should be a drop-in replacement to bitsandbytes with much better performance. Kernels are from https://github.com/NetEase-FuXi/EETQ.git - eetq: 8 bit quantization, doesn't require specific model. Should be a drop-in replacement to bitsandbytes with much better performance. Kernels are from https://github.com/NetEase-FuXi/EETQ.git
- gptq: 4 bit quantization. Requires a specific GTPQ quantized model: https://hf.co/models?search=gptq. text-generation-inference will use exllama (faster) kernels whereever possible, and use triton kernel (wider support) when it's not. AWQ has faster kernels - gptq: 4 bit quantization. Requires a specific GTPQ quantized model: https://hf.co/models?search=gptq. text-generation-inference will use exllama (faster) kernels wherever possible, and use triton kernel (wider support) when it's not. AWQ has faster kernels
- bitsandbytes: 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 - bitsandbytes: 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
- bitsandbytes-nf4: 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 - bitsandbytes-nf4: 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
- bitsandbytes-fp4: Bitsandbytes 4bit. nf4 should be preferred in most cases but maybe this one has better perplexity performance for you model - bitsandbytes-fp4: Bitsandbytes 4bit. nf4 should be preferred in most cases but maybe this one has better perplexity performance for you model

6
launcher/src/main.rs
View File

@ -21,16 +21,16 @@ mod env_runtime;
#[derive(Clone, Copy, Debug, ValueEnum)] #[derive(Clone, Copy, Debug, ValueEnum)]
enum Quantization { enum Quantization {
/// 4 bit quantization. Requires a specific GTPQ quantized model: /// 4 bit quantization. Requires a specific AWQ quantized model:
/// https://hf.co/models?search=awq. /// https://hf.co/models?search=awq.
/// Should replace GPTQ models whereever possible because of the better latency /// Should replace GPTQ models wherever possible because of the better latency
Awq, Awq,
/// 8 bit quantization, doesn't require specific model. /// 8 bit quantization, doesn't require specific model.
/// Should be a drop-in replacement to bitsandbytes with much better performance. /// Should be a drop-in replacement to bitsandbytes with much better performance.
/// Kernels are from https://github.com/NetEase-FuXi/EETQ.git /// Kernels are from https://github.com/NetEase-FuXi/EETQ.git
Eetq, Eetq,
/// 4 bit quantization. Requires a specific GTPQ quantized model: https://hf.co/models?search=gptq. /// 4 bit quantization. Requires a specific GTPQ quantized model: https://hf.co/models?search=gptq.
/// text-generation-inference will use exllama (faster) kernels whereever possible, and use /// text-generation-inference will use exllama (faster) kernels wherever possible, and use
/// triton kernel (wider support) when it's not. /// triton kernel (wider support) when it's not.
/// AWQ has faster kernels. /// AWQ has faster kernels.
Gptq, Gptq,