Skip to content

Releases: Tencent/TurboTransformers

TurboTransformers v0.5.1

25 Nov 09:46
6387402
Compare
Choose a tag to compare

Albert Model uses the model-aware-allocator.

TurboTransformers v0.5.0

19 Nov 12:18
ecaf698
Compare
Choose a tag to compare

Add Model Aware Allocator for Bert Model.

TurboTransformers v0.4.2

19 Aug 09:12
8fbbd2a
Compare
Choose a tag to compare

Add Quantized Bert using onnxruntime.

TurboTransformers v0.4.1

12 Aug 02:23
e623096
Compare
Choose a tag to compare

Using onnxruntime-cpu as CPU backend, parallel to our own home-grown implementation.

TurboTransformer v0.3.0

30 Jun 04:09
72097bf
Compare
Choose a tag to compare

Support Transformer decoder used in OpenNMT-py.
New GPU memory allocator.
Be Compatible with Pytorch v1.5.0.

TurboTransformer v0.2.1

11 Jun 03:58
a47bbf1
Compare
Choose a tag to compare

Add blis to BLAS options.

TurboTransformer v0.0.1

25 Apr 14:34
21ddad5
Compare
Choose a tag to compare

Bert Acceleration on CPU and GPU.