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