6 Commits

Author	SHA1	Message	Date
Nicolas Patry	9c4b4f0da0	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).	2024-01-15 17:42:58 +01:00
Nicolas Patry	b4cb982e49	Simplifying our internal cargo dependencies. (#1529)	2024-01-07 12:04:14 +01:00
Laurent Mazare	d35f0a1376	Bump the crate version to 0.3.3. (#1490)	2023-12-28 13:38:30 +01:00
Laurent Mazare	94817dac56	Bump the crate version to 0.3.2. (#1452)	2023-12-17 05:34:53 -06:00
Laurent Mazare	a209ce8ceb	Update for 0.3.1. (#1324)	2023-11-11 18:48:52 +00:00
Radamés Ajna	e5dc8cb4f4	[Wasm] BLIP Example (#1183) ... * blip wasm start * fix dependency issue, move token stream here * vanilla js worker * roll back vscode * spell	2023-10-26 07:24:02 +01:00