text-generation-inference/server
Victor SANH 1fff6746ab
Fix position ids logic instantiation of idefics vision part (#1064)
Problem and fix is described here:
https://huggingface.co/HuggingFaceM4/idefics-9b/discussions/9

---------

Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2023-09-26 15:41:15 +02:00
..
custom_kernels feat(server): Rework model loading (#344) 2023-06-08 14:51:52 +02:00
exllama_kernels feat: add cuda memory fraction (#659) 2023-07-24 11:43:58 +02:00
tests Rebased #617 (#868) 2023-08-28 11:43:47 +02:00
text_generation_server Fix position ids logic instantiation of idefics vision part (#1064) 2023-09-26 15:41:15 +02:00
.gitignore Add AWQ quantization inference support (#1019) (#1054) 2023-09-25 15:31:27 +02:00
Makefile Add AWQ quantization inference support (#1019) (#1054) 2023-09-25 15:31:27 +02:00
Makefile-awq Add AWQ quantization inference support (#1019) (#1054) 2023-09-25 15:31:27 +02:00
Makefile-flash-att feat(server): use latest flash attention commit (#543) 2023-07-04 20:23:55 +02:00
Makefile-flash-att-v2 feat(server): flash attention v2 (#624) 2023-07-18 16:21:18 +02:00
Makefile-vllm Backport https://github.com/vllm-project/vllm/pull/936 (#977) 2023-09-04 15:00:19 +02:00
poetry.lock Add AWQ quantization inference support (#1019) (#1054) 2023-09-25 15:31:27 +02:00
pyproject.toml Add AWQ quantization inference support (#1019) (#1054) 2023-09-25 15:31:27 +02:00
README.md feat(router): refactor API and add openAPI schemas (#53) 2023-02-03 12:43:37 +01:00
requirements.txt New release. (#941) 2023-08-29 14:28:22 +02:00

Text Generation Inference Python gRPC Server

A Python gRPC server for Text Generation Inference

Install

make install

Run

make run-dev