docs: Fix missing --gpu all flag in Docker run commands (#2026)

adding the --gpu all flag to Docker run commands
for meta-reference-gpu distributions ensures models are loaded into GPU
instead of CPU.

Remove docs for meta-reference-quantized-gpu
The distribution was removed in #1887
but these files were left behind.


Fixes: #1798

# What does this PR do?
Fixes doc to add --gpu all command to docker run

[//]: # (If resolving an issue, uncomment and update the line below)
Closes #1798

## Test Plan
[Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.*]

verified in docker documentation but untested

---------

Signed-off-by: Derek Higgins <derekh@redhat.com>

llama_stack/templates/meta-reference-gpu/doc_template.md

@@ -69,6 +69,7 @@ LLAMA_STACK_PORT=8321
 docker run \
   -it \
   --pull always \
+  --gpu all \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ~/.llama:/root/.llama \
   llamastack/distribution-{{ name }} \
@@ -82,6 +83,7 @@ If you are using Llama Stack Safety / Shield APIs, use:
 docker run \
   -it \
   --pull always \
+  --gpu all \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ~/.llama:/root/.llama \
   llamastack/distribution-{{ name }} \