73d089bb90
There are a number that are no longer needed at all:
- 0003-embeddings: Embeddings entirely overhauled on master
- 0008-ensure-KV-cache-is-fully-defragmented: KV caching entirely
overhauled on master
- 0019-metal-add-mean-kernel-14267: Merged upstream
- 0020-CUDA-add-mean-operation-14313: Merged upstream
Branch: GraniteFour
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
|
||
|---|---|---|
| .. | ||
| 0001-ggml-backend-malloc-and-free-using-the-same-compiler.patch | ||
| 0002-pretokenizer.patch | ||
| 0003-clip-unicode.patch | ||
| 0004-solar-pro.patch | ||
| 0005-fix-deepseek-deseret-regex.patch | ||
| 0006-maintain-ordering-for-rules-for-grammar.patch | ||
| 0007-sort-devices-by-score.patch | ||
| 0008-add-phony-target-ggml-cpu-for-all-cpu-variants.patch | ||
| 0009-remove-amx.patch | ||
| 0010-fix-string-arr-kv-loading.patch | ||
| 0011-ollama-debug-tensor.patch | ||
| 0012-add-ollama-vocab-for-grammar-support.patch | ||
| 0013-add-argsort-and-cuda-copy-for-i32.patch | ||
| 0014-graph-memory-reporting-on-failure.patch | ||
| 0015-ggml-Export-GPU-UUIDs.patch | ||
| 0016-temporary-prevent-rocm-cuda-mixed-loading.patch | ||