Trying to install VLLM nightly as recommended for running this FP8 Dynamic, but getting 'requirements are unsatisfiable' output from uv, below.
On my x86_64 server, uv won't install that nightly.
I'll check in VLLM issues but flagging here in case I'm missing something obvious about your VLLM instructions.
uv pip install --upgrade --force-reinstall vllm --prerelease=allow --torch-backend=auto --extra-index-url https://wheels.vllm.ai/nightly/ Using Python 3.11.11 environment at: vllm × No solution found when resolving dependencies: ╰─▶ Because only vllm==0.16.0rc1.dev109+gd95b4be47 is available and vllm==0.16.0rc1.dev109+gd95b4be47 has no wheels with a matching platform tag (e.g., manylinux_2_39_x86_64), we can conclude that all versions of vllm cannot be used. And because you require vllm, we can conclude that your requirements are unsatisfiable.
hint: `vllm` was found on https://wheels.vllm.ai/nightly/, but not at the requested version (all of:
vllm<0.16.0rc1.dev109+gd95b4be47
vllm>0.16.0rc1.dev109+gd95b4be47
). A compatible version may be available on a subsequent index (e.g., https://pypi.org/simple). By default, uv will only consider versions that are
published on the first index that contains a given package, to avoid dependency confusion attacks. If all indexes are equally trusted, use `--index-strategy
unsafe-best-match` to consider all versions from all indexes, regardless of the order in which they were defined.
hint: Wheels are available for `vllm` (v0.16.0rc1.dev109+gd95b4be47) on the following platform: `manylinux_2_31_aarch64`
