huggingface/optimum

Pull Requests Commits

Release: v1.2.2

echarlaix committed 2 years ago

0107c1c6

Bump `huggingface_hub` version to be able to use `evaluate` & `protobuf` fix (#205)

philschmid committed 2 years ago

Verified 5a002603

Compare optimized models vs. transformers models (#194)

fxmarty committed 3 years ago

Verified 1b989408

Patch ORTTrainer's compatibility with DeepSpeed (#148)

JingyaHuang committed 3 years ago

Verified 021ae43f

Update PR docs to use `doc-builder push` (#200)

Mishig Davaadorj committed 3 years ago

Verified 583e8d68

Allow onnxruntime quantization preprocessor for dynamic quantization (#196)

fxmarty committed 3 years ago

Verified f5a74133

Add a CONTRIBUTING.md and CODE_OF_CONDUCT.md (#190)

fxmarty committed 3 years ago

Verified 50cf2468

Fix logging typo (#192)

regisss committed 3 years ago

Verified cf91bd72

Add quantization ort multiple choice example (#144)

echarlaix committed 3 years ago

Verified 5a28d9f1

Add keywords for arguments in `OnnxConfig` wrappers (#185)

JingyaHuang committed 3 years ago

Verified 822efaca

echarlaix committed 3 years ago

Verified 8171e8cf

Extend python required version to 3.7 and higher (#176)

echarlaix committed 3 years ago

Verified 78793bec

use correct sample (#179)

philschmid committed 3 years ago

Verified b3ff258a

Fix version number shown in doc build (#177)

lewtun committed 3 years ago

Verified 71783183

Fix ONNX Runtime FusionOptions import (#175)

echarlaix committed 3 years ago

Verified 6aa47f96

Add version number to doc build (#168)

lewtun committed 3 years ago

Verified 800e01c4

echarlaix committed 3 years ago

fd6c0137

Improve Documentation (#170)

philschmid committed 3 years ago

Verified 5653a167

Fix rouge keyerror (#167)

JingyaHuang committed 3 years ago

Verified 37a0d86b

[ORTTrainer] Fix CI of ORTTrainer (#165)

JingyaHuang committed 3 years ago

Verified 3a284468

[fix] Warning when loading ORTModels with pipelines of not supported class type (#164)

philschmid committed 3 years ago

Verified 3b522e4d

Ensure attention mask is on same device as inputs IDs during text generation (#162)

lewtun committed 3 years ago

Verified c9761991

[Patch] Add loss for ORT inference (#152)

JingyaHuang committed 3 years ago

Verified 1c4b5b1c

Add a top level init (#160)

fxmarty committed 3 years ago

Verified f9a87e07

Clean workflows (#158)

echarlaix committed 3 years ago

Verified 81b85fa6

Add ORT inference (#113)

philschmid committed 3 years ago

Verified a31e59ed

Fix import (#159)

echarlaix committed 3 years ago

Verified 74172026

Add deepspeed configuration for upcoming tests (#157)

JingyaHuang committed 3 years ago

Verified daeb496d

echarlaix committed 3 years ago

6cb44f08

Fix pretrained ort configuration loading (#156)

echarlaix committed 3 years ago

Verified 73f1ee9d

Older