Optimum

Latest version: v1.23.3

Safety actively analyzes 679296 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 8 of 22

1.13.1

Fix ONNX fp16 export that broke in 1.13.0.

What's Changed
* Fix wrong dtype in the ONNX export by fxmarty in https://github.com/huggingface/optimum/pull/1369
* Fix tests collection for TFLite export and trigger TFLite tests only when relevant by fxmarty in https://github.com/huggingface/optimum/pull/1368
* upgrade min compatible optimum-intel version by echarlaix in https://github.com/huggingface/optimum/pull/1371
* Fix fp16 ONNX export test by fxmarty in https://github.com/huggingface/optimum/pull/1373

1.13

The codebase is fully validated for the latest version of Habana SDK, SynapseAI v1.13.

- Upgrade to SynapseAI 1.13 563 regisss

Fine-tuning Llama2-70B, Falcon-180B and BLOOM-7B

Added examples for fine-tuning Llama2-70B and Falcon-180B on Gaudi2 and BLOOM-7B on first-gen Gaudi.

- Enable llama2-70b LoRA finetuning 527 mandy-li
- Add Deepspeed zero3 configuration to run bloom-7b on Gaudi1 487
- Enable Falcon 180B 537 hlahkar

Llama2 fp8 inference

- Add llamav2 fp8 inference 542 bgoldberg-habana

Mistral

- Add mistral support for generation 496 sywangyi

Optimizations

- Remove GPTJ dma before mha 468 BaihuiJin
- Enable llama attention softmax in bf16 521 schoi-habana
- Add load_meta_device option to reduce host RAM 529 jiminha
- Improve llama performance and reduce memory consumption by updating sin/cos cache when inferring more than max position embeddings (4096) 532 puneeshkhanna
- Add hash_with_views arg for Falcon inference perf 534 schoi-habana
- Automate skip_hash_with_views for text generation with Falcon 544 regisss

Improved text generation

- Allow multi prompts 479 ssarkar2
- Growing bucket for beam 450 ssarkar2
- Some models have extra inputs, pad them too 488 ssarkar2
- Refactor run generation 523 bgoldberg-habana
- Fix setting of reuse cache 553 puneeshkhanna
- No need to unsqueeze input_id in prepare_inputs_for_generation 559 sywangyi
- Adding lm eval script 541 bgoldberg-habana

1.13.0

OpenVINO

Weight only 4-bit quantization

* Add weight only 4-bit quantization support by AlexKoff88 in https://github.com/huggingface/optimum-intel/pull/469

bash
optimum-cli export openvino --model gpt2 --weight-format int4_sym_g128 ov_model


Stateful

* Add support for stateful models by eaidova in https://github.com/huggingface/optimum-intel/pull/493

New architectures

Whisper

* Add support for export and inference for whisper models by eaidova in https://github.com/huggingface/optimum-intel/pull/470

1.12.4

* Fix compatibility with `transformers` v4.37.0 by echarlaix in https://github.com/huggingface/optimum-intel/pull/515
* Fix compatibility with `transformers` v4.37.0 by echarlaix in https://github.com/huggingface/optimum-intel/pull/527

1.12.3

* Fix compatibility with `diffusers` v0.25.0 by eaidova in https://github.com/huggingface/optimum-intel/pull/497
* Modify minimum required `transformers` version by echarlaix in https://github.com/huggingface/optimum-intel/pull/498

1.12.2

* Fix compatibility with timm latest release by echarlaix in https://github.com/huggingface/optimum-intel/pull/482
* Fix causallm weights compression via quantizer by eaidova 484
* Fix pkv dtype by jiqing-feng 481
* Fix compatibility causallm models export with optimum 1.15 by eaidova 487
* Fix trainer compatibility with transformers>=4.36.0 by echarlaix 490
* Fix openvino export by eaidova 470
* Fix INC quantized model loading by echarlaix 492

Page 8 of 22

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.