fix(python-backend): make JIT subprocesses work on hosts of any size

[richiejp]

Put ninja on the PATH by putting the venv bin in the PATH correctly. Instead of trying to patch up the activate script we just do the necessary bits ourselves; it's very simple and shouldn't change.

---

Two related runtime fixes for Python backends that JIT-compile CUDA
kernels at first model load (FlashInfer, PyTorch inductor, triton):

1. libbackend.sh: replace source ${EDIR}/venv/bin/activate with a
   minimal manual setup (_activateVenv: export VIRTUAL_ENV, prepend
   PATH, unset PYTHONHOME) computed from $EDIR at runtime. uv venv
   and python -m venv both bake the create-time absolute path into
   bin/activate (e.g. VIRTUAL_ENV='/vllm/venv' from the Docker build
   stage), so sourcing activate on a relocated venv — copied out of
   the build container and unpacked at an arbitrary backend dir —
   prepends a stale, non-existent path to $PATH. Pip-installed CLI
   tools (e.g. ninja, used by FlashInfer's NVFP4 GEMM JIT) are then
   never found and the load aborts with FileNotFoundError. Doing the
   env setup ourselves matches what uv run does internally and
   sidesteps the relocation problem entirely. Generic — every Python
   backend benefits.

2. vllm/run.sh: replace ninja's default -j$(nproc)+2 with an adaptive
   MAX_JOBS = min(nproc, (MemAvailable-4)/4). Each concurrent
   nvcc/cudafe++ peaks at multiple GiB; the default OOM-kills on
   memory-tight hosts (e.g. a 16 GiB desktop loading a 27B NVFP4
   model) but underutilises 100-core / 1 TB boxes. User-set MAX_JOBS
   still wins. Also pin NVCC_THREADS=2 unless overridden.

Refs: vllm-project/vllm#20079

Assisted-by: Claude:claude-opus-4-7 [Edit] [Bash]