Separate quantized phi-3 implementation. (#2157)

* Separate quantized phi-3 implementation. * Integrate the quantized phi3 model.= * Small fixes, get the generation to work properly. * Keep the old llama implementation around. * Change the default.
2025-06-18 19:47:12 +00:00 · 2024-05-04 10:14:57 +02:00
parent 59b18d974e
commit b13a82a438
7 changed files with 323 additions and 12 deletions
--- a/candle-core/src/sort.rs
+++ b/candle-core/src/sort.rs
@ -178,7 +178,7 @@ impl crate::CustomOp1 for ArgSort {
            device.metal_device(),
            &command_buffer,
            kernels,
-            &name,
+            name,
            nrows,
            ncols,
            ncols_pad,