mirror of https://github.com/ollama/ollama.git
35fda7b4af
We don't get valid UUIDs for AMD GPUs on Windows, so the best option is to use the ordinal IDs. This brings us in line with what we currently do on the Ollama server - the only exception is AMD GPUs on Linux, which falls back to using ordinal IDs. The GGML implementation has no fallback but it doesn't appear to occur for any of the GPUs that we support. It's also possible that there are collisions between ordinal IDs for different libraries - however the only places where we use them are AMD on Windows and Metal on Mac, which can never occur on the same system. |
||
|---|---|---|
| .. | ||
| 0001-ggml-backend-malloc-and-free-using-the-same-compiler.patch | ||
| 0002-pretokenizer.patch | ||
| 0003-embeddings.patch | ||
| 0004-clip-unicode.patch | ||
| 0005-solar-pro.patch | ||
| 0006-fix-deepseek-deseret-regex.patch | ||
| 0007-maintain-ordering-for-rules-for-grammar.patch | ||
| 0008-ensure-KV-cache-is-fully-defragmented.patch | ||
| 0009-sort-devices-by-score.patch | ||
| 0010-add-phony-target-ggml-cpu-for-all-cpu-variants.patch | ||
| 0011-remove-amx.patch | ||
| 0012-fix-string-arr-kv-loading.patch | ||
| 0013-ollama-debug-tensor.patch | ||
| 0014-add-ollama-vocab-for-grammar-support.patch | ||
| 0015-add-argsort-and-cuda-copy-for-i32.patch | ||
| 0016-graph-memory-reporting-on-failure.patch | ||
| 0017-ggml-Export-GPU-UUIDs.patch | ||
| 0018-temporary-prevent-rocm-cuda-mixed-loading.patch | ||
| 0019-metal-add-mean-kernel-14267.patch | ||
| 0020-CUDA-add-mean-operation-14313.patch | ||