llama_cpp_for_radxa_dragon_.../docs
jeromew 384c0076bc
docs: Update build.md: HSA_OVERRIDE_GFX_VERSION clarification (#21331)
The `HSA_OVERRIDE_GFX_VERSION` variable can be used in ROCm to override an unsupported target architecture with a similar but supported target architecture.

This does not and has never worked on Windows. I think the clarification could avoid driving Windows people towards this solution that does not work.
2026-04-03 21:05:14 +08:00
..
android
backend ggml-zendnn : add MUL_MAT_ID op support for MoE models (#21315) 2026-04-03 12:19:08 +03:00
development
multimodal
ops ggml-zendnn : add MUL_MAT_ID op support for MoE models (#21315) 2026-04-03 12:19:08 +03:00
android.md
autoparser.md common/parser: add proper reasoning tag prefill reading (#20424) 2026-03-19 16:58:21 +01:00
build-riscv64-spacemit.md
build-s390x.md
build.md docs: Update build.md: HSA_OVERRIDE_GFX_VERSION clarification (#21331) 2026-04-03 21:05:14 +08:00
docker.md CI : Enable CUDA and Vulkan ARM64 runners and fix CI/CD (#21122) 2026-03-30 20:24:37 +02:00
function-calling.md
install.md
llguidance.md
multimodal.md mtmd: Add DeepSeekOCR Support (#17400) 2026-03-25 19:57:40 +01:00
ops.md ggml-zendnn : add MUL_MAT_ID op support for MoE models (#21315) 2026-04-03 12:19:08 +03:00
preset.md
speculative.md