PR #3748 DeepSpeed-Triton for Inference

[squash] styoun/triton fp16 transformer (#530)

jeffra committed 2 years ago

Triton kernels and BERT inference using triton in float16 (#459)

stephen-youn committed 2 years ago

readme for blog

styoun committed 2 years ago

typo in readme

styoun committed 2 years ago

readme

styoun committed 2 years ago

readme

styoun committed 2 years ago

readme

styoun committed 2 years ago

readme

styoun committed 2 years ago

plots

styoun committed 2 years ago

readme

styoun committed 2 years ago

readme

styoun committed 2 years ago

readme

styoun committed 2 years ago

readme

styoun committed 2 years ago

readme

styoun committed 2 years ago

typo in readme

styoun committed 2 years ago

readme revision after the feedbacks

styoun committed 2 years ago

typo

styoun committed 2 years ago

refined the writing in readme

styoun committed 2 years ago

readme

styoun committed 2 years ago

readme

styoun committed 2 years ago

removed obsolete comments from matmul_ext.py

styoun committed 2 years ago

typo

styoun committed 2 years ago

Merge branch 'master' into staging-triton-bert-v1

jeffra committed 2 years ago

readme change from pr comments

styoun committed 2 years ago

Merge branch 'staging-triton-bert-v1' of https://github.com/microsoft/DeepSpeed into staging-triton-bert-v1

styoun committed 2 years ago

Merge branch 'master' into staging-triton-bert-v1

jeffra committed 2 years ago

removed obsolete codes and comments

styoun committed 2 years ago

Merge branch 'staging-triton-bert-v1' of https://github.com/microsoft/DeepSpeed into staging-triton-bert-v1

styoun committed 2 years ago

readme

styoun committed 2 years ago

Merge branch 'master' into staging-triton-bert-v1

stephen-youn committed 2 years ago

Merge branch 'master' into staging-triton-bert-v1

jeffra committed 2 years ago

DeepSpeed DeepSpeed-Triton for Inference #3748 Merged

DeepSpeed
DeepSpeed-Triton for Inference
#3748

Merged