huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 04:14:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

support h100

Browse Source
This commit is contained in:
OlivierDehaene 2023-12-11 13:40:50 +01:00
parent 008733313c
commit 6c2ac3b5fb
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Dockerfile
View File

@ -157,7 +157,7 @@ RUN make build-vllm-cuda
# Build megablocks
FROM kernel-builder as megablocks-builder
RUN pip install git+https://github.com/OlivierDehaene/megablocks@3de516d9b774ea5dd1b79c68e2c475880f3983e7
RUN pip install git+https://github.com/OlivierDehaene/megablocks@181709df192de9a941fdf3a641cdc65a0462996e
# Text Generation Inference base image
FROM nvidia/cuda:12.1.0-base-ubuntu20.04 as base

2
server/Makefile
View File

@ -17,7 +17,7 @@ gen-server:
touch text_generation_server/pb/__init__.py
install-megablocks:
pip install git+https://github.com/OlivierDehaene/megablocks@3de516d9b774ea5dd1b79c68e2c475880f3983e7
pip install git+https://github.com/OlivierDehaene/megablocks@181709df192de9a941fdf3a641cdc65a0462996e
install: gen-server
pip install pip --upgrade