pin gguf where the image actually reads it (v0.4.96 follow-up)

0.4.96 added gguf>=0.10.0 to requirements.txt, which was half right. Two
things about how this image is built that the change missed:

  * requirements-oci.txt has carried `gguf>=0.9.0` since June, so the
    dependency was not undeclared after all -- only unsatisfiable. diffusers'
    GGUFQuantizationConfig refuses anything below 0.10.0 ("requires both
    PyTorch and GGUF>=0.10.0"), so a 0.9.x install satisfies the line and
    still cannot load a GGUF pipeline component. Pinned to 0.10.0.

  * Dockerfile.oci COPIES requirements.txt, requirements-nvidia.txt and
    requirements-vulkan.txt into the build and then deletes them unused: the
    RUN installs `-r /tmp/requirements-oci.txt` and nothing else. So for the
    container image, requirements-oci.txt is the only list that counts.
    requirements.txt still matters for a host build.sh install, and the
    in-image upgrade reads BOTH, which is why the entry there is not wasted.

No rebuild needed to ship it: coderai-upgrade's delta install takes
requirements.txt plus requirements-oci.txt, installs what is new, and the
autoupgrade commits the result onto the image tag.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01S8LAP3ueNzQJtwzhgVbq66

packaging/common/requirements-oci.txt

@@ -12,7 +12,10 @@ tiktoken>=0.5.0
 tokenizers>=0.15.0
 protobuf>=3.20.0
 optimum-quanto>=0.2.0
-gguf>=0.9.0
+# 0.10.0, not 0.9: diffusers' GGUFQuantizationConfig refuses anything older
+# ("requires both PyTorch and GGUF>=0.10.0"), so a 0.9.x install satisfies this
+# line and still cannot load a GGUF pipeline component.
+gguf>=0.10.0
 turboquant-py>=0.1.0  # optional TurboQuant embedding-vector quantization backend (1-4 bit)
 
 # Native wheels are built by packaging/linux/Dockerfile.oci with CUDA+Vulkan enabled.