- 29 Oct, 2024 1 commit
-
-
xuxzh1 authored
-
- 03 Jul, 2023 1 commit
-
-
Nicolas Patry authored
# What does this PR do? This adds a non flash version of MPT. Flash is harder because we need to create a bias ready cuda kernel of flash attention. Fixes https://github.com/huggingface/text-generation-inference/issues/361 Fixes https://github.com/huggingface/text-generation-inference/issues/491 Fixes https://github.com/huggingface/text-generation-inference/issues/290
-
