Nicolas Patry f97fcd4712 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).

2024-01-05 14:29:41 +01:00

..

main.rs

Metal quantized modifications proposal.

2024-01-05 14:29:41 +01:00

training.rs

Infer the config for llama2-c. (#1208)

2023-10-28 19:00:39 +01:00