Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Quantized GGUF style #1523

Merged
merged 10 commits into from
Jan 17, 2024
Merged

Quantized GGUF style #1523

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
9c4b4f0
Metal quantized modifications proposal.
Nov 18, 2023
2cd1e59
Cleanup.
Narsil Jan 5, 2024
61ad8d9
Fix the rebase.
Narsil Jan 5, 2024
c8c603c
Removing the fences speeds everything up and *is* correct this time...
Narsil Jan 5, 2024
3aefc70
Cleanup the fence.
Narsil Jan 5, 2024
9ef0403
After rebase.
Narsil Jan 11, 2024
b2db5ad
Bad code removal.
Narsil Jan 15, 2024
3dbf65e
Rebase after phi2 merge + fix replit default to CPU.
Narsil Jan 15, 2024
f1b624c
Making the CI happy.
Narsil Jan 15, 2024
1c0404a
More happy tests.
Narsil Jan 15, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
122 changes: 52 additions & 70 deletions candle-core/examples/tensor-tools.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
use candle_core::quantized::{gguf_file, k_quants, QTensor};
use candle_core::{Device, Result, Tensor};
use candle_core::quantized::{gguf_file, GgmlDType, QTensor};
use candle_core::{Device, Result};
use clap::{Parser, Subcommand, ValueEnum};
use rayon::prelude::*;

Expand All @@ -11,22 +11,17 @@ enum QuantizationMode {
}

impl QuantizationMode {
fn quantize(
&self,
name: &str,
tensor: QTensor,
default: fn(&Tensor) -> Result<QTensor>,
) -> Result<QTensor> {
fn quantize(&self, name: &str, tensor: QTensor, dtype: GgmlDType) -> Result<QTensor> {
match self {
Self::Llama => {
// Same behavior as the llama.cpp quantization.
let should_quantize = name.ends_with(".weight") && tensor.rank() == 2;
if should_quantize {
let tensor = tensor.dequantize(&Device::Cpu)?;
if name == "output.weight" {
QTensor::quantize::<k_quants::BlockQ6K>(&tensor)
QTensor::quantize(&tensor, GgmlDType::Q6K)
} else {
default(&tensor)
QTensor::quantize(&tensor, dtype)
}
} else {
Ok(tensor)
Expand Down Expand Up @@ -60,6 +55,27 @@ enum Quantization {
F32,
}

impl Quantization {
fn dtype(&self) -> GgmlDType {
match self {
Quantization::Q4_0 => GgmlDType::Q4_0,
Quantization::Q4_1 => GgmlDType::Q4_1,
Quantization::Q5_0 => GgmlDType::Q5_0,
Quantization::Q5_1 => GgmlDType::Q5_1,
Quantization::Q8_0 => GgmlDType::Q8_0,
Quantization::Q8_1 => GgmlDType::Q8_1,
Quantization::Q2k => GgmlDType::Q2K,
Quantization::Q3k => GgmlDType::Q3K,
Quantization::Q4k => GgmlDType::Q4K,
Quantization::Q5k => GgmlDType::Q5K,
Quantization::Q6k => GgmlDType::Q6K,
Quantization::Q8k => GgmlDType::Q8K,
Quantization::F16 => GgmlDType::F16,
Quantization::F32 => GgmlDType::F32,
}
}
}

#[derive(ValueEnum, Debug, Clone)]
enum Format {
Safetensors,
Expand Down Expand Up @@ -134,7 +150,12 @@ struct Args {
command: Command,
}

fn run_ls(file: &std::path::PathBuf, format: Option<Format>, verbose: bool) -> Result<()> {
fn run_ls(
file: &std::path::PathBuf,
format: Option<Format>,
verbose: bool,
device: &Device,
) -> Result<()> {
let format = match format {
Some(format) => format,
None => match Format::infer(file) {
Expand Down Expand Up @@ -200,7 +221,7 @@ fn run_ls(file: &std::path::PathBuf, format: Option<Format>, verbose: bool) -> R
}
Format::Ggml => {
let mut file = std::fs::File::open(file)?;
let content = candle_core::quantized::ggml_file::Content::read(&mut file)?;
let content = candle_core::quantized::ggml_file::Content::read(&mut file, device)?;
let mut tensors = content.tensors.into_iter().collect::<Vec<_>>();
tensors.sort_by(|a, b| a.0.cmp(&b.0));
for (name, qtensor) in tensors.iter() {
Expand Down Expand Up @@ -241,47 +262,18 @@ fn run_quantize_safetensors(
}
println!("tensors: {}", tensors.len());

let quantize_fn = match q {
Quantization::Q4_0 => QTensor::quantize::<k_quants::BlockQ4_0>,
Quantization::Q4_1 => QTensor::quantize::<k_quants::BlockQ4_1>,
Quantization::Q5_0 => QTensor::quantize::<k_quants::BlockQ5_0>,
Quantization::Q5_1 => QTensor::quantize::<k_quants::BlockQ5_1>,
Quantization::Q8_0 => QTensor::quantize::<k_quants::BlockQ8_0>,
Quantization::Q8_1 => QTensor::quantize::<k_quants::BlockQ8_1>,
Quantization::Q2k => QTensor::quantize::<k_quants::BlockQ2K>,
Quantization::Q3k => QTensor::quantize::<k_quants::BlockQ3K>,
Quantization::Q4k => QTensor::quantize::<k_quants::BlockQ4K>,
Quantization::Q5k => QTensor::quantize::<k_quants::BlockQ5K>,
Quantization::Q6k => QTensor::quantize::<k_quants::BlockQ6K>,
Quantization::Q8k => QTensor::quantize::<k_quants::BlockQ8K>,
Quantization::F16 => QTensor::quantize::<half::f16>,
Quantization::F32 => QTensor::quantize::<f32>,
};
let block_size = match q {
Quantization::Q4_0 => k_quants::QK4_0,
Quantization::Q4_1 => k_quants::QK4_1,
Quantization::Q5_0 => k_quants::QK5_0,
Quantization::Q5_1 => k_quants::QK5_1,
Quantization::Q8_0 => k_quants::QK8_0,
Quantization::Q8_1 => k_quants::QK8_1,
Quantization::Q2k
| Quantization::Q3k
| Quantization::Q4k
| Quantization::Q5k
| Quantization::Q6k
| Quantization::Q8k => k_quants::QK_K,
Quantization::F16 | Quantization::F32 => 1,
};
let dtype = q.dtype();
let block_size = dtype.block_size();

let qtensors = tensors
.into_par_iter()
.map(|(name, tensor)| {
let should_quantize = tensor.rank() == 2 && tensor.dim(1)? % block_size == 0;
println!(" quantizing {name} {tensor:?} {should_quantize}");
let tensor = if should_quantize {
quantize_fn(&tensor)?
QTensor::quantize(&tensor, dtype)?
} else {
QTensor::quantize::<f32>(&tensor)?
QTensor::quantize(&tensor, GgmlDType::F32)?
};
Ok((name, tensor))
})
Expand All @@ -294,13 +286,17 @@ fn run_quantize_safetensors(
Ok(())
}

fn run_dequantize(in_file: std::path::PathBuf, out_file: std::path::PathBuf) -> Result<()> {
fn run_dequantize(
in_file: std::path::PathBuf,
out_file: std::path::PathBuf,
device: &Device,
) -> Result<()> {
let mut in_file = std::fs::File::open(in_file)?;
let content = gguf_file::Content::read(&mut in_file)?;
let mut tensors = std::collections::HashMap::new();
for (tensor_name, _) in content.tensor_infos.iter() {
let tensor = content.tensor(&mut in_file, tensor_name)?;
let tensor = tensor.dequantize(&Device::Cpu)?;
let tensor = content.tensor(&mut in_file, tensor_name, device)?;
let tensor = tensor.dequantize(device)?;
tensors.insert(tensor_name.to_string(), tensor);
}
candle_core::safetensors::save(&tensors, out_file)?;
Expand All @@ -312,6 +308,7 @@ fn run_quantize(
out_file: std::path::PathBuf,
q: Quantization,
qmode: QuantizationMode,
device: &Device,
) -> Result<()> {
if in_files.is_empty() {
candle_core::bail!("no specified input files")
Expand All @@ -337,31 +334,15 @@ fn run_quantize(
let content = gguf_file::Content::read(&mut in_)?;
println!("tensors: {}", content.tensor_infos.len());

let quantize_fn = match q {
Quantization::Q4_0 => QTensor::quantize::<k_quants::BlockQ4_0>,
Quantization::Q4_1 => QTensor::quantize::<k_quants::BlockQ4_1>,
Quantization::Q5_0 => QTensor::quantize::<k_quants::BlockQ5_0>,
Quantization::Q5_1 => QTensor::quantize::<k_quants::BlockQ5_1>,
Quantization::Q8_0 => QTensor::quantize::<k_quants::BlockQ8_0>,
Quantization::Q8_1 => QTensor::quantize::<k_quants::BlockQ8_1>,
Quantization::Q2k => QTensor::quantize::<k_quants::BlockQ2K>,
Quantization::Q3k => QTensor::quantize::<k_quants::BlockQ3K>,
Quantization::Q4k => QTensor::quantize::<k_quants::BlockQ4K>,
Quantization::Q5k => QTensor::quantize::<k_quants::BlockQ5K>,
Quantization::Q6k => QTensor::quantize::<k_quants::BlockQ6K>,
Quantization::Q8k => QTensor::quantize::<k_quants::BlockQ8K>,
Quantization::F16 => QTensor::quantize::<half::f16>,
Quantization::F32 => QTensor::quantize::<f32>,
};

let dtype = q.dtype();
let qtensors = content
.tensor_infos
.par_iter()
.map(|(name, _)| {
println!(" quantizing {name}");
let mut in_file = std::fs::File::open(&in_files[0])?;
let tensor = content.tensor(&mut in_file, name)?;
let tensor = qmode.quantize(name, tensor, quantize_fn)?;
let tensor = content.tensor(&mut in_file, name, device)?;
let tensor = qmode.quantize(name, tensor, dtype)?;
Ok((name, tensor))
})
.collect::<Result<Vec<_>>>()?;
Expand All @@ -381,6 +362,7 @@ fn run_quantize(

fn main() -> anyhow::Result<()> {
let args = Args::parse();
let device = Device::Cpu;
match args.command {
Command::Ls {
files,
Expand All @@ -392,16 +374,16 @@ fn main() -> anyhow::Result<()> {
if multiple_files {
println!("--- {file:?} ---");
}
run_ls(file, format.clone(), verbose)?
run_ls(file, format.clone(), verbose, &device)?
}
}
Command::Quantize {
in_file,
out_file,
quantization,
mode,
} => run_quantize(&in_file, out_file, quantization, mode)?,
Command::Dequantize { in_file, out_file } => run_dequantize(in_file, out_file)?,
} => run_quantize(&in_file, out_file, quantization, mode, &device)?,
Command::Dequantize { in_file, out_file } => run_dequantize(in_file, out_file, &device)?,
}
Ok(())
}
Loading
Loading