.. |
0001-cuda.patch
|
d7d7e99662
llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)
|
2 月之前 |
0002-pretokenizer.patch
|
d7d7e99662
llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)
|
2 月之前 |
0003-embeddings.patch
|
d7d7e99662
llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)
|
2 月之前 |
0004-clip-unicode.patch
|
d7d7e99662
llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)
|
2 月之前 |
0005-solar-pro.patch
|
d7d7e99662
llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)
|
2 月之前 |
0006-conditional-fattn.patch
|
d7d7e99662
llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)
|
2 月之前 |
0007-add-mllama-support.patch
|
d7d7e99662
llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)
|
2 月之前 |
0008-add-unpad-operator.patch
|
d7d7e99662
llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)
|
2 月之前 |
0009-fix-deepseek-deseret-regex.patch
|
d7d7e99662
llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)
|
2 月之前 |
0010-Maintain-ordering-for-rules-for-grammar.patch
|
d7d7e99662
llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)
|
2 月之前 |
0011-llama-Ensure-KV-cache-is-fully-defragmented.patch
|
d7d7e99662
llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)
|
2 月之前 |
0012-use-dynamic-backend-loading-for-clip.patch
|
d7d7e99662
llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)
|
2 月之前 |
0013-sort-devices-by-score.patch
|
d7d7e99662
llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)
|
2 月之前 |
0014-add-phony-target-ggml-cpu-for-all-cpu-variants.patch
|
d7d7e99662
llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)
|
2 月之前 |
0015-use-std-filesystem-path-instead-of-wstring.patch
|
ba7d31240e
fix: own lib/ollama directory
|
2 月之前 |
0016-remove-amx.patch
|
ba7d31240e
fix: own lib/ollama directory
|
2 月之前 |
0017-fix-clip-compiler-error.patch
|
ba7d31240e
fix: own lib/ollama directory
|
2 月之前 |
0018-add-phi4-support.patch
|
ba7d31240e
fix: own lib/ollama directory
|
2 月之前 |