Laurent Mazare aa207f2dd9 Print some per-step timings in stable-diffusion. (#520) ...

* Skeleton files for neon support of quantization.

* SIMD version for q4 vecdot.

* Also simdify the q6k multiplication.

* Add some timings to stable-diffusion.

2023-08-20 05:45:12 +01:00

..

bert

Add a simple Module trait and implement it for the various nn layers (#500)

2023-08-18 09:38:22 +01:00

bigcode

Add a simple Module trait and implement it for the various nn layers (#500)

2023-08-18 09:38:22 +01:00

custom-ops

Relax the requirements on CustomOp. (#486)

2023-08-17 11:12:05 +01:00

dinov2

Use the hub to retrieve dinov2 model weights. (#507)

2023-08-18 18:27:31 +01:00

falcon

Add a simple Module trait and implement it for the various nn layers (#500)

2023-08-18 09:38:22 +01:00

llama

Add a simple Module trait and implement it for the various nn layers (#500)

2023-08-18 09:38:22 +01:00

llama2-c

Add a simple Module trait and implement it for the various nn layers (#500)

2023-08-18 09:38:22 +01:00

llama_multiprocess

Add a simple Module trait and implement it for the various nn layers (#500)

2023-08-18 09:38:22 +01:00

mnist-training

Add a simple Module trait and implement it for the various nn layers (#500)

2023-08-18 09:38:22 +01:00

musicgen

Add a simple Module trait and implement it for the various nn layers (#500)

2023-08-18 09:38:22 +01:00

quantized

Line up the llama.cpp implementation with the candle one. (#518)

2023-08-19 20:12:07 +01:00

stable-diffusion

Print some per-step timings in stable-diffusion. (#520)

2023-08-20 05:45:12 +01:00

whisper

Add a simple Module trait and implement it for the various nn layers (#500)

2023-08-18 09:38:22 +01:00