Merge branch 'main' into drifkin/array-head-count-simple

b2b270ad · Devon Rifkin · 20c5fd39 · 2bb69b40 · b2b270ad · 20c5fd39
Commit b2b270ad authored Jun 23, 2025 by Devon Rifkin
20 changed files
--- a/llama/llama.go
+++ b/llama/llama.go
--- a/llama/mllama.cpp
+++ b/llama/mllama.cpp
--- a/llama/mllama.h
+++ b/llama/mllama.h
--- a/llama/patches/0001-ggml-backend-malloc-and-free-using-the-same-compiler.patch
+++ b/llama/patches/0001-ggml-backend-malloc-and-free-using-the-same-compiler.patch
--- a/llama/patches/0002-pretokenizer.patch
+++ b/llama/patches/0002-pretokenizer.patch
--- a/llama/patches/0003-embeddings.patch
+++ b/llama/patches/0003-embeddings.patch
--- a/llama/patches/0004-clip-unicode.patch
+++ b/llama/patches/0004-clip-unicode.patch
--- a/llama/patches/0005-solar-pro.patch
+++ b/llama/patches/0005-solar-pro.patch
--- a/llama/patches/0006-add-mllama-support.patch
+++ b/llama/patches/0006-add-mllama-support.patch
--- a/llama/patches/0008-fix-deepseek-deseret-regex.patch
+++ b/llama/patches/0008-fix-deepseek-deseret-regex.patch
--- a/llama/patches/0007-add-unpad-operator.patch
+++ b/llama/patches/0007-add-unpad-operator.patch
--- a/llama/patches/0009-maintain-ordering-for-rules-for-grammar.patch
+++ b/llama/patches/0009-maintain-ordering-for-rules-for-grammar.patch
--- a/llama/patches/0010-ensure-KV-cache-is-fully-defragmented.patch
+++ b/llama/patches/0010-ensure-KV-cache-is-fully-defragmented.patch
--- a/llama/patches/0011-sort-devices-by-score.patch
+++ b/llama/patches/0011-sort-devices-by-score.patch
--- a/llama/patches/0012-add-phony-target-ggml-cpu-for-all-cpu-variants.patch
+++ b/llama/patches/0012-add-phony-target-ggml-cpu-for-all-cpu-variants.patch
--- a/llama/patches/0013-remove-amx.patch
+++ b/llama/patches/0013-remove-amx.patch
--- a/llama/patches/0014-fix-string-arr-kv-loading.patch
+++ b/llama/patches/0014-fix-string-arr-kv-loading.patch
--- a/llama/patches/0015-ollama-debug-tensor.patch
+++ b/llama/patches/0015-ollama-debug-tensor.patch
--- a/llama/patches/0016-add-ollama-vocab-for-grammar-support.patch
+++ b/llama/patches/0016-add-ollama-vocab-for-grammar-support.patch
--- a/llama/patches/0015-add-argsort-and-cuda-copy-for-i32.patch
+++ b/llama/patches/0015-add-argsort-and-cuda-copy-for-i32.patch