Zack Angelo a2e9d41b20 use softmax_last_dim (metal and cuda kernel) in llama attention layer (#2572)

2024-10-23 20:07:09 +02:00

..

generation

Include topk sampling in the quantized example. (#2005)

2024-04-04 09:27:54 +02:00

models

use softmax_last_dim (metal and cuda kernel) in llama attention layer (#2572)

2024-10-23 20:07:09 +02:00

pipelines

Sketch the candle-transformers crate. (#147)

2023-07-12 13:49:31 +01:00

lib.rs

Move the common quantized-nn code to a shared module. (#1063)

2023-10-09 06:22:22 +01:00

object_detection.rs

Soft Non-Maximum Suppression (#2400)

2024-08-10 07:57:52 +02:00

quantized_nn.rs

Use the fast RmsNorm in the quantized model. (#1904)

2024-03-21 18:49:35 +01:00

quantized_var_builder.rs

Add a quantized version of recurrent-gemma. (#2054)

2024-04-13 20:07:01 +02:00

utils.rs

Use cat for faster MQA computation. (#2043)

2024-04-12 09:15:10 +02:00