Quantized GGUF style (#1523)

* Metal quantized modifications proposal.

- Add a device param, wherever needed.
- Create new QMetal storage thing that implements QuantizedType.
- Update everywhere needed.

Fix Python.

Fixing examples.

Fix: fmt + clippy + stub.

Moving everything around.

Only missing the actual implems.

Fixing everything + adding dequantized kernels.

More work.

Fixing matmul.

Fmt + Clippy

Some clippy fixes.

Working state.

Q2K Metal -> Bugged (also present in GGML).
Q4K CPU -> Bugged (present previously, new test catch it).
Q5K CPU -> Bugged (present previously).
Q8_1 Both -> Never really implemented it seems
Q8K metal -> Never implemented in metal

Fixing Q2K bug (present in ggml).

* Cleanup.

* Fix the rebase.

* Removing the fences speeds everything up and *is* correct this time...

* Cleanup the fence.

* After rebase.

* Bad code removal.

* Rebase after phi2 merge + fix replit default to CPU.

* Making the CI happy.

* More happy tests.

---------

Co-authored-by: Nicolas Patry <nicolas@Nicolass-MacBook-Pro.local>

candle-examples/examples/whisper/main.rs

@@ -557,8 +557,10 @@ fn main() -> Result<()> {
     println!("loaded mel: {:?}", mel.dims());
 
     let mut model = if args.quantized {
-        let vb =
-            candle_transformers::quantized_var_builder::VarBuilder::from_gguf(&weights_filename)?;
+        let vb = candle_transformers::quantized_var_builder::VarBuilder::from_gguf(
+            &weights_filename,
+            &device,
+        )?;
         Model::Quantized(m::quantized_model::Whisper::load(&vb, config)?)
     } else {
         let vb =