New Dockerfile, still dummy app, testing minimal req file. v6

README.md

@@ -1,26 +1 @@
----
-title: LLM Server
-emoji: 🐨
-colorFrom: indigo
-colorTo: yellow
-sdk: docker
-app_port: 7860
-pinned: false
-short_description: LLM Server for Team Gen KI (GPU goes here)
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
-
-
-HTTP Clone:
-
-    git clone https://huggingface.co/spaces/TeamGenKI/LLM-Server
-
-SSH Clone:
-
-    git clone git@hf.co:spaces/TeamGenKI/LLM-Server
-
-
-Hosted location:
-
-    https://teamgenki-llmserver.hf.space
+# LLM Server

_requirements.txt

@@ -1,57 +0,0 @@
-accelerate==1.1.1
-annotated-types==0.7.0
-anyio==4.6.2.post1
-bitsandbytes==0.44.1
-certifi==2024.8.30
-charset-normalizer==3.4.0
-click==8.1.7
-fastapi==0.115.5
-filelock==3.16.1
-fsspec==2024.10.0
-h11==0.14.0
-huggingface-hub==0.26.3
-idna==3.10
-inquirerpy==0.3.4
-Jinja2==3.1.4
-MarkupSafe==3.0.2
-mpmath==1.3.0
-networkx==3.4.2
-numpy==2.1.3
-nvidia-cublas-cu12==12.4.5.8
-nvidia-cuda-cupti-cu12==12.4.127
-nvidia-cuda-nvrtc-cu12==12.4.127
-nvidia-cuda-runtime-cu12==12.4.127
-nvidia-cudnn-cu12==9.1.0.70
-nvidia-cufft-cu12==11.2.1.3
-nvidia-curand-cu12==10.3.5.147
-nvidia-cusolver-cu12==11.6.1.9
-nvidia-cusparse-cu12==12.3.1.170
-nvidia-nccl-cu12==2.21.5
-nvidia-nvjitlink-cu12==12.4.127
-nvidia-nvtx-cu12==12.4.127
-packaging==24.2
-pfzy==0.3.4
-prompt_toolkit==3.0.48
-psutil==6.1.0
-pydantic==2.10.2
-pydantic_core==2.27.1
-python-dotenv==1.0.1
-PyYAML==6.0.2
-regex==2024.11.6
-requests==2.32.3
-router==0.1
-safetensors==0.4.5
-setuptools==75.6.0
-sniffio==1.3.1
-starlette==0.41.3
-sympy==1.13.1
-tokenizers==0.20.3
-torch==2.5.1
-tqdm==4.67.1
-transformers==4.46.3
-triton==3.1.0
-typing_extensions==4.12.2
-urllib3==2.2.3
-utils==1.0.2
-uvicorn==0.32.1
-wcwidth==0.2.13