[Doc]: Latest release instructions produce python dependency issues

[rofinn]

📚 The doc issue

Following the current release instructions

> sudo docker run -it --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --net=host --ipc=host vault.habana.ai
/gaudi-docker/1.19.0/ubuntu22.04/habanalabs/pytorch-installer-2.5.1:latest
Unable to find image 'vault.habana.ai/gaudi-docker/1.19.0/ubuntu22.04/habanalabs/pytorch-installer-2.5.1:latest' locally
latest: Pulling from gaudi-docker/1.19.0/ubuntu22.04/habanalabs/pytorch-installer-2.5.1
6414378b6477: Pull complete
82f0cbb256c2: Pull complete
d50a5ec5680f: Pull complete
b84305bbd298: Pull complete
9b3008227e6e: Pull complete
bd6ead514a6f: Pull complete
...
> git clone https://github.com/HabanaAI/vllm-fork.git
Cloning into 'vllm-fork'...
remote: Enumerating objects: 61832, done.
remote: Counting objects: 100% (16/16), done.
remote: Compressing objects: 100% (15/15), done.
remote: Total 61832 (delta 6), reused 2 (delta 1), pack-reused 61816 (from 4)
Receiving objects: 100% (61832/61832), 56.17 MiB | 28.99 MiB/s, done.
Resolving deltas: 100% (48354/48354), done.
> cd vllm-fork/
> git checkout v0.6.4.post2+Gaudi-1.19.0
Note: switching to 'v0.6.4.post2+Gaudi-1.19.0'.
...
> pip install -r requirements-hpu.txt
Ignoring fastapi: markers 'python_version < "3.9"' don't match your environment
Ignoring six: markers 'python_version > "3.11"' don't match your environment
Ignoring setuptools: markers 'python_version > "3.11"' don't match your environment
...
Successfully built vllm-hpu-extension
Installing collected packages: triton, sentencepiece, pyairports, zipp, xxhash, websockets, vllm-hpu-extension, uvloop, tomli, tabulate, sniffio, safetensors, rpds-py, pyzm
q, python-dotenv, pydantic-core, pycountry, pyarrow, prometheus_client, pillow, partial-json-parser, numpy, nest-asyncio, msgspec, msgpack, llvmlite, lark, jiter, interegul
ar, httptools, h11, fsspec, exceptiongroup, einops, distro, diskcache, dill, cloudpickle, click, annotated-types, uvicorn, tiktoken, setuptools-scm, referencing, pydantic,
opencv-python-headless, numba, multiprocess, importlib_metadata, huggingface-hub, httpcore, gguf, anyio, watchfiles, tokenizers, starlette, lm-format-enforcer, jsonschema-s
pecifications, httpx, transformers, prometheus-fastapi-instrumentator, openai, jsonschema, fastapi, ray, mistral_common, datasets, compressed-tensors, outlines
  Attempting uninstall: numpy
    Found existing installation: numpy 1.23.5
    Uninstalling numpy-1.23.5:
      Successfully uninstalled numpy-1.23.5
  Attempting uninstall: fsspec
    Found existing installation: fsspec 2024.10.0
    Uninstalling fsspec-2024.10.0:
      Successfully uninstalled fsspec-2024.10.0
  Attempting uninstall: pydantic
    Found existing installation: pydantic 1.10.13
    Uninstalling pydantic-1.10.13:
      Successfully uninstalled pydantic-1.10.13
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflict
s.
neural-compressor-pt 3.2 requires numpy==1.23.5; python_version < "3.12", but you have numpy 1.26.4 which is incompatible.
neural-compressor-pt 3.2 requires pydantic==1.10.13, but you have pydantic 2.10.6 which is incompatible.

Suggest a potential alternative/fix

No response

Before submitting a new issue...

• Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

[rofinn]

Issue also occurs with 1.19.1 docker image.

[rofinn]

Seems like the only viable option if you don't want to deal with a bunch of manual dependency management is to just run habana_main.

[PatrykWo]

@rofinn thank you for the issue. We will review that.
We have same changes to the documentation under review #699.