huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Don't install flahs on the CPU tests.

Browse Source
This commit is contained in:
Nicolas Patry 2024-06-04 13:31:43 +00:00
parent d841a4900a
commit 76fef7b1d2
3 changed files with 8 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.github/workflows/tests.yaml vendored
View File

@ -68,7 +68,7 @@ jobs:
~/.cargo/git ~/.cargo/git
- name: Install - name: Install
run: | run: |
make install make install-cpu
- name: Run server tests - name: Run server tests
run: | run: |
pip install pytest pip install pytest

6
Makefile
View File

@ -1,6 +1,9 @@
install-server: install-server:
cd server && make install cd server && make install
install-server-cpu:
cd server && make install-server
install-router: install-router:
cd router && cargo install --path . cd router && cargo install --path .
@ -12,6 +15,9 @@ install-benchmark:
install: install-server install-router install-launcher install: install-server install-router install-launcher
install-cpu: install-server-cpu install-router install-launcher
server-dev: server-dev:
cd server && make run-dev cd server && make run-dev

2
server/Makefile
View File

@ -23,7 +23,7 @@ install-server: gen-server
pip install -e ".[bnb, accelerate, quantize, peft, outlines]" pip install -e ".[bnb, accelerate, quantize, peft, outlines]"
install: install-server install-cuda install: install-cuda
echo "Installed server" echo "Installed server"
install-cuda: install-server install-flash-attention-v2-cuda install-vllm-cuda install-flash-attention install-cuda: install-server install-flash-attention-v2-cuda install-vllm-cuda install-flash-attention