deps(conda): use transformers-env with vllm,exllama(2) (#1554)

* deps(conda): use transformers with vllm

* join vllm, exllama, exllama2, split petals

backend/python/vllm/Makefile

@@ -1,8 +1,6 @@
 .PHONY: vllm
 vllm:
-	@echo "Creating virtual environment..."
-	@conda env create --name vllm --file vllm.yml
-	@echo "Virtual environment created."
+	$(MAKE) -C ../common-env/transformers
 
 .PHONY: run
 run:

backend/python/vllm/run.sh

@@ -6,7 +6,7 @@
 export PATH=$PATH:/opt/conda/bin
 
 # Activate conda environment
-source activate vllm
+source activate transformers
 
 # get the directory where the bash script is located
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"

backend/python/vllm/test.sh

@@ -3,7 +3,7 @@
 ## A bash script wrapper that runs the transformers server with conda
 
 # Activate conda environment
-source activate vllm
+source activate transformers
 
 # get the directory where the bash script is located
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"

backend/python/vllm/vllm.yml

@@ -1,99 +0,0 @@
-name: vllm
-channels:
-  - defaults
-dependencies:
-  - _libgcc_mutex=0.1=main
-  - _openmp_mutex=5.1=1_gnu
-  - bzip2=1.0.8=h7b6447c_0
-  - ca-certificates=2023.08.22=h06a4308_0
-  - ld_impl_linux-64=2.38=h1181459_1
-  - libffi=3.4.4=h6a678d5_0
-  - libgcc-ng=11.2.0=h1234567_1
-  - libgomp=11.2.0=h1234567_1
-  - libstdcxx-ng=11.2.0=h1234567_1
-  - libuuid=1.41.5=h5eee18b_0
-  - ncurses=6.4=h6a678d5_0
-  - openssl=3.0.11=h7f8727e_2
-  - pip=23.2.1=py311h06a4308_0
-  - python=3.11.5=h955ad1f_0
-  - readline=8.2=h5eee18b_0
-  - setuptools=68.0.0=py311h06a4308_0
-  - sqlite=3.41.2=h5eee18b_0
-  - tk=8.6.12=h1ccaba5_0
-  - wheel=0.41.2=py311h06a4308_0
-  - xz=5.4.2=h5eee18b_0
-  - zlib=1.2.13=h5eee18b_0
-  - pip:
-      - aiosignal==1.3.1
-      - anyio==3.7.1
-      - attrs==23.1.0
-      - certifi==2023.7.22
-      - charset-normalizer==3.3.0
-      - click==8.1.7
-      - cmake==3.27.6
-      - fastapi==0.103.2
-      - filelock==3.12.4
-      - frozenlist==1.4.0
-      - fsspec==2023.9.2
-      - grpcio==1.59.0
-      - h11==0.14.0
-      - httptools==0.6.0
-      - huggingface-hub==0.17.3
-      - idna==3.4
-      - jinja2==3.1.2
-      - jsonschema==4.19.1
-      - jsonschema-specifications==2023.7.1
-      - lit==17.0.2
-      - markupsafe==2.1.3
-      - mpmath==1.3.0
-      - msgpack==1.0.7
-      - networkx==3.1
-      - ninja==1.11.1
-      - numpy==1.26.0
-      - nvidia-cublas-cu11==11.10.3.66
-      - nvidia-cuda-cupti-cu11==11.7.101
-      - nvidia-cuda-nvrtc-cu11==11.7.99
-      - nvidia-cuda-runtime-cu11==11.7.99
-      - nvidia-cudnn-cu11==8.5.0.96
-      - nvidia-cufft-cu11==10.9.0.58
-      - nvidia-curand-cu11==10.2.10.91
-      - nvidia-cusolver-cu11==11.4.0.1
-      - nvidia-cusparse-cu11==11.7.4.91
-      - nvidia-nccl-cu11==2.14.3
-      - nvidia-nvtx-cu11==11.7.91
-      - packaging==23.2
-      - pandas==2.1.1
-      - protobuf==4.24.4
-      - psutil==5.9.5
-      - pyarrow==13.0.0
-      - pydantic==1.10.13
-      - python-dateutil==2.8.2
-      - python-dotenv==1.0.0
-      - pytz==2023.3.post1
-      - pyyaml==6.0.1
-      - ray==2.7.0
-      - referencing==0.30.2
-      - regex==2023.10.3
-      - requests==2.31.0
-      - rpds-py==0.10.4
-      - safetensors==0.4.0
-      - sentencepiece==0.1.99
-      - six==1.16.0
-      - sniffio==1.3.0
-      - starlette==0.27.0
-      - sympy==1.12
-      - tokenizers==0.14.1
-      - torch==2.0.1
-      - tqdm==4.66.1
-      - transformers==4.34.0
-      - triton==2.0.0
-      - typing-extensions==4.8.0
-      - tzdata==2023.3
-      - urllib3==2.0.6
-      - uvicorn==0.23.2
-      - uvloop==0.17.0
-      - vllm==0.2.0
-      - watchfiles==0.20.0
-      - websockets==11.0.3
-      - xformers==0.0.22
-prefix: /opt/conda/envs/vllm