docs: clarify Windows CUDA GPU architecture support

[LauraGPT]

Summary

• document that the current windows-x64-cuda llama.cpp runtime asset targets CUDA architecture 86
• tell RTX 50 / Blackwell users to use CPU binaries or build with CMAKE_CUDA_ARCHITECTURES=120 until a dedicated asset exists
• keep the release workflow documentation test covering the sm_120 warning

Validation

• python3 -m pytest runtime/llama.cpp/tests/test_release_workflow.py -q
• python3 -m compileall -q runtime/llama.cpp/tests/test_release_workflow.py
• git diff --check

Fixes #3289

[gemini-code-assist]

Code Review

This pull request updates the documentation and release workflow tests to provide instructions for compiling and running on RTX 50 / Blackwell GPUs. The reviewer correctly pointed out a critical error across all modified files: the Blackwell architecture has a compute capability of 10.0 (sm_100) rather than 12.0 (sm_120). Using the incorrect sm_120 value would result in compilation failures. The feedback is highly actionable and provides the correct CMake flags and architecture values to resolve the issue.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

[gemini-code-assist]

The Blackwell architecture (RTX 50 series) has a compute capability of 10.0 (sm_100), not 12.0 (sm_120). Using -DCMAKE_CUDA_ARCHITECTURES=120 will result in a compilation error because sm_120 is not a valid CUDA architecture. It should be updated to 10.0 / sm_100 / -DCMAKE_CUDA_ARCHITECTURES=100.

Suggested change:

The current Windows CUDA package targets CUDA architecture 86. RTX 50 / Blackwell
GPUs report compute capability 10.0 (`sm_100`) and should use the CPU package or
build from source with `-DCMAKE_CUDA_ARCHITECTURES=100` until a dedicated CUDA
asset is published.

[gemini-code-assist]

The Blackwell architecture (RTX 50 series) has a compute capability of 10.0 (sm_100), not 12.0 (sm_120). Using -DCMAKE_CUDA_ARCHITECTURES=120 will result in a compilation error because sm_120 is not a valid CUDA architecture. It should be updated to 10.0 / sm_100 / -DCMAKE_CUDA_ARCHITECTURES=100.

Suggested change:

当前 Windows CUDA 包面向 CUDA architecture 86。RTX 50 / Blackwell GPU 会报告
compute capability 10.0（`sm_100`），在专用 CUDA 产物发布前，请使用 CPU 包，或从
源码构建并设置 `-DCMAKE_CUDA_ARCHITECTURES=100`。

[gemini-code-assist]

The Blackwell architecture (RTX 50 series) uses compute capability 10.0 (sm_100). Specifying -DCMAKE_CUDA_ARCHITECTURES=120 will cause nvcc to fail with an unsupported GPU architecture error. It should be -DCMAKE_CUDA_ARCHITECTURES=100.

Suggested change:

cmake -B build-cuda -DCMAKE_BUILD_TYPE=Release -DGGML_CUDA=ON \
  -DCMAKE_CUDA_ARCHITECTURES=100

[gemini-code-assist]

The Blackwell architecture (RTX 50 series) reports compute capability 10.0 (sm_100), not 12.0 (sm_120).

Suggested change:

Use the matching `CMAKE_CUDA_ARCHITECTURES` value for your GPU. RTX 50 /
Blackwell cards report compute capability 10.0 (`sm_100`), so the current
`windows-x64-cuda` prebuilt package for architecture 86 will not cover those
cards.

[gemini-code-assist]

Update the test assertions to match the correct Blackwell compute capability of 10.0 (sm_100) and the corresponding CMake flag -DCMAKE_CUDA_ARCHITECTURES=100.

Suggested change

	assert "CMAKE_CUDA_ARCHITECTURES=120" in readme
	assert "sm_120" in readme
	assert "CMAKE_CUDA_ARCHITECTURES=100" in readme
	assert "sm_100" in readme