@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / a8fda4f661
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 16, 23:15 UTC

Seperate dev requirements into lint and test (#5474)

Antoni Baum committed Jun 13, 2024 at 11:22 UTC a8fda4f66131e211ac1e64f6b1d74123e0347a1c
4 files changed +42 -36
Dockerfile
+2
@@ -27,6 +27,8 @@ RUN --mount=type=cache,target=/root/.cache/pip \
27 pip install -r requirements-cuda.txt
28
29 # install development dependencies
30 +COPY requirements-lint.txt requirements-lint.txt
31 +COPY requirements-test.txt requirements-test.txt
32 COPY requirements-dev.txt requirements-dev.txt
33 RUN --mount=type=cache,target=/root/.cache/pip \
34 pip install -r requirements-dev.txt
requirements-dev.txt
+4 -36
@@ -1,37 +1,5 @@
1 -# formatting
2 -yapf==0.32.0
3 -toml==0.10.2
4 -tomli==2.0.1
5 -ruff==0.1.5
6 -codespell==2.3.0
7 -isort==5.13.2
8 -clang-format==18.1.5
1 +-r requirements-lint.txt
2 +-r requirements-test.txt
3
10 -# type checking
11 -mypy==1.9.0
12 -types-PyYAML
13 -types-requests
14 -types-setuptools
15 -
16 -# testing
17 -pytest
18 -tensorizer>=2.9.0
19 -pytest-forked
20 -pytest-asyncio
21 -pytest-rerunfailures
22 -pytest-shard
23 -
24 -# testing utils
25 -awscli
26 -einops # required for MPT
27 -httpx
28 -peft
29 -requests
30 -ray
31 -sentence-transformers # required for embedding
32 -
33 -# Benchmarking
34 -aiohttp
35 -
36 -# quantization
37 -bitsandbytes==0.42.0
4 +# Avoid adding requirements directly to this file.
5 +# Instead, modify the two files referenced above.
requirements-lint.txt new
+14
@@ -0,0 +1,14 @@
1 +# formatting
2 +yapf==0.32.0
3 +toml==0.10.2
4 +tomli==2.0.1
5 +ruff==0.1.5
6 +codespell==2.3.0
7 +isort==5.13.2
8 +clang-format==18.1.5
9 +
10 +# type checking
11 +mypy==1.9.0
12 +types-PyYAML
13 +types-requests
14 +types-setuptools
requirements-test.txt new
+22
@@ -0,0 +1,22 @@
1 +# testing
2 +pytest
3 +tensorizer>=2.9.0
4 +pytest-forked
5 +pytest-asyncio
6 +pytest-rerunfailures
7 +pytest-shard
8 +
9 +# testing utils
10 +awscli
11 +einops # required for MPT
12 +httpx
13 +peft
14 +requests
15 +ray
16 +sentence-transformers # required for embedding
17 +
18 +# Benchmarking
19 +aiohttp
20 +
21 +# quantization
22 +bitsandbytes==0.42.0