Laurent Mazare 8de0ce6cba Add more QMMV cuda kernels. (#2077) ...

* Add more QMMV cuda kernels.

* Enable the new kernels.

* Adapt the testing.

2024-04-18 08:36:43 +02:00

..

avx.rs

Fix a couple typos (#1451)

2023-12-17 05:20:05 -06:00

cuda.rs

Add more QMMV cuda kernels. (#2077)

2024-04-18 08:36:43 +02:00

dummy_cuda.rs

Cuda acceleration for quantized model. (#1754)

2024-02-25 18:11:47 +01:00

dummy_metal.rs

Cuda acceleration for quantized model. (#1754)

2024-02-25 18:11:47 +01:00

ggml_file.rs

Cuda acceleration for quantized model. (#1754)

2024-02-25 18:11:47 +01:00

gguf_file.rs

Quantized GGUF style (#1523)

2024-01-17 10:27:58 +01:00

k_quants.rs

Bugfix for dequantizing q5k layers. (#1569)

2024-01-11 23:15:11 +01:00

metal.rs

Handle the batch dimension in quantized MMV on metal. (#2022)

2024-04-06 20:02:24 +02:00

mod.rs

Fix dequantization. (#1823)

2024-03-08 23:12:13 +01:00

neon.rs

Simpler repro for the neon optimization issue + bugfix (#1544)

2024-01-07 20:21:49 +01:00

simd128.rs

No need for the even constraint on vecdot-q40-q80. (#1202)

2023-10-28 07:23:59 +01:00

utils.rs

Use the gelu-erf activation. (#969)

2023-09-26 22:30:21 +01:00