mirror of
https://github.com/ollama/ollama.git
synced 2026-07-04 06:41:39 +00:00
624cada952
* discover: use the SBSA CUDA build on JetPack 7 (L4T r38+) JetPack 7 supports SBSA-based CUDA, so the standard cuda_v13 build — shipped in the base linux-arm64 package, and given the Orin arch (CC 8.7) in #16628 — runs on these devices. JETSON_JETPACK=7 previously selected a nonexistent jetpack7 runner, so runner.go skipped every CUDA library and discovery fell back to CPU. The L4T releases JetPack 7 uses (r38 on Thor, r39 on Orin) also hit the unrecognized branch, and install.sh warned the version was unsupported. Map JetPack 7+ (L4T r38 and newer) to cuda_v13 (returned as "" from cudaJetpack); no Jetson-specific download is needed, so install.sh no longer warns. Fixes #16602 * discover: fall back to standard CUDA when the JetPack runner is absent Per review, drop the L4T-version mapping (in cudaJetpack and install.sh) and instead clear the jetpack override in runner.go when the detected cuda_jetpack runner isn't installed. Normal discovery then selects the standard cuda_v13 build, which supports Orin (CC 8.7) on JetPack 7. |
||
|---|---|---|
| .. | ||
| amd.go | ||
| amd_test.go | ||
| cpu_linux.go | ||
| cpu_windows.go | ||
| cuda_compat.go | ||
| cuda_compat_test.go | ||
| gpu.go | ||
| gpu_darwin.go | ||
| gpu_info_darwin.h | ||
| gpu_info_darwin.m | ||
| llama_server.go | ||
| llama_server_test.go | ||
| native_probe.go | ||
| native_probe_linux.go | ||
| native_probe_linux_nocgo.go | ||
| native_probe_platform.go | ||
| native_probe_stub.go | ||
| native_probe_test.go | ||
| native_probe_windows.go | ||
| runner.go | ||
| runner_test.go | ||
| types.go | ||
| vulkan.go | ||
| vulkan_refine_stub.go | ||
| vulkan_refine_windows.go | ||