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-wasm-tests/tests/quantized_tests.rs

@@ -40,7 +40,7 @@ fn quantized_matmul_neg() -> Result<()> {
         ]
     );
 
-    let qtensor = quantized::QTensor::new(rhs_t, (4, 64))?;
+    let qtensor = quantized::QTensor::new(quantized::QStorage::Cpu(Box::new(rhs_t)), (4, 64))?;
     let matmul = quantized::QMatMul::from_qtensor(qtensor)?;
     let res = matmul.forward(&tensor_lhs)?;
     assert_eq!(