ivarflakstad e90bcdcc7c Metal: f16 and bf16 where_cond + benchmark (#1545) ...

* Use cfg to seperate benchmark results based on features

* Add metal where_cond for f16 and bf16. Add benchmark

* Remove allow pragma

* Avoid some unnecessary returns.

* Improve benchmarks layout

* Updated feature separated benchmarks

---------

Co-authored-by: Laurent <laurent.mazare@gmail.com>

2024-01-12 11:18:11 +01:00

..

bert

Speed up bert with approx gelu (#1410)

2023-12-06 17:46:37 +01:00

bigcode

Adapt more examples to the updated safetensor api. (#947)

2023-09-23 21:26:03 +01:00

blip

Add a KV cache to marian decoding. (#1226)

2023-10-31 08:47:44 +00:00

convmixer

Convmixer example (#1074)

2023-10-11 19:51:10 +01:00

custom-ops

Metal: f16 and bf16 where_cond + benchmark (#1545)

2024-01-12 11:18:11 +01:00

dinov2

Adapt more examples to the updated safetensor api. (#947)

2023-09-23 21:26:03 +01:00

distilbert

Distibert (#1366)

2023-11-24 15:09:14 +00:00

efficientnet

Adapt more examples to the updated safetensor api. (#947)

2023-09-23 21:26:03 +01:00

falcon

Use the new hub helper function. (#1484)

2023-12-26 09:44:30 +01:00

jina-bert

Use the hub model file when possible. (#1190)

2023-10-26 20:00:50 +01:00

llama

fix index_pos bug when kv cache is disabled. (#1517)

2024-01-06 11:43:01 +01:00

llama2-c

Infer the config for llama2-c. (#1208)

2023-10-28 19:00:39 +01:00

llama_multiprocess

Use the new hub helper function. (#1484)

2023-12-26 09:44:30 +01:00

mamba-minimal

Fix for mamba 2.8b. (#1472)

2023-12-23 11:01:39 +01:00

marian-mt

Add a KV cache to marian decoding. (#1226)

2023-10-31 08:47:44 +00:00

mistral

Helper function to load sharded safetensors files (#1481)

2023-12-25 21:49:21 +01:00

mixtral

Helper function to load sharded safetensors files (#1481)

2023-12-25 21:49:21 +01:00

mnist-training

Allow for different behavior between training and eval (#1213)

2023-10-29 07:53:09 +01:00

musicgen

Fix lints for clippy 1.75. (#1494)

2023-12-28 20:26:20 +01:00

onnx

Add more models to the onnx example. (#1273)

2023-11-05 16:57:26 +01:00

phi

Pin the revision used for phi-v2 + make it the default. (#1572)

2024-01-12 09:19:30 +01:00

quantized

Support mistral instruct v0.2. (#1475)

2023-12-23 16:18:49 +01:00

quantized-t5

Add info about MADLAD-400 in readme files (#1287)

2023-11-07 15:21:59 +01:00

reinforcement-learning

Add Policy Gradient to Reinforcement Learning examples (#1500)

2023-12-30 09:01:29 +01:00

replit-code

Add the quantized mpt model. (#1123)

2023-10-18 16:29:38 +01:00

repvgg

Mention VGG in the readme. (#1573)

2024-01-12 09:59:29 +01:00

resnet

Expose the larger resnets (50/101/152) in the example. (#1131)

2023-10-19 13:48:28 +01:00

segment-anything

Add negative prompts to segment-anything. (#1000)

2023-09-30 06:17:42 +01:00

stable-diffusion

Format properly the Stable Diffusion example run with params (#1511)

2024-01-01 11:13:35 +01:00

stable-lm

Quantized version of StableLM. (#1058)

2023-10-08 15:42:38 +01:00

t5

Helper function to load sharded safetensors files (#1481)

2023-12-25 21:49:21 +01:00

trocr

Update readme.md (#1322)

2023-11-12 09:46:19 +00:00

vgg

Allow for different behavior between training and eval (#1213)

2023-10-29 07:53:09 +01:00

vit

Readme updates. (#1134)

2023-10-20 09:08:39 +01:00

whisper

Use the whisper-v3 tokenizer now that it has been added. (#1337)

2023-11-16 22:10:31 +00:00

wuerstchen

Remove some unusued bits. (#1067)

2023-10-09 19:49:57 +01:00

yi

Helper function to load sharded safetensors files (#1481)

2023-12-25 21:49:21 +01:00

yolo-v3

Do not implement Module for BatchNorm. (#1513)

2024-01-01 10:13:13 +01:00

yolo-v8

Fix linspace implementation (#1358)

2023-11-23 07:35:13 +00:00

onnx_basics.rs

[ONNX] Support a couple more ops. (#1284)

2023-11-06 22:44:58 +01:00