Merge pull request #342 from janhq/update-submodule-2024-12-18-17-01 · janhq/cortex.llamacpp@0cbb3c3

Commit

Merge pull request #342 from janhq/update-submodule-2024-12-18-17-01

Update llama.cpp submodule to latest release b4354

jan-service-account authored Dec 18, 2024

2 parents a0c43bf + 1cf77c1 commit 0cbb3c3

+1 −1		README.md
+0 −6		convert_hf_to_gguf.py
+0 −1		convert_hf_to_gguf_update.py
+6 −2		examples/server/README.md
+54 −20		examples/server/server.cpp
+12 −4		examples/server/tests/unit/test_completion.py
+59 −0		examples/server/tests/unit/test_embedding.py
+23 −0		examples/server/tests/unit/test_rerank.py
+13 −6		examples/server/utils.hpp
+0 −1		ggml/src/ggml-alloc.c
+1 −1		ggml/src/ggml-cpu/CMakeLists.txt
+3 −0		ggml/src/ggml-cpu/ggml-cpu.cpp
+16 −0		ggml/src/ggml-impl.h
+1 −1		ggml/src/ggml-vulkan/vulkan-shaders/soft_max.comp
+26 −43		ggml/src/ggml.c
+1 −1		scripts/sync-ggml.last
+8 −26		src/llama.cpp
+1 −0		tests/CMakeLists.txt
+2 −2		tests/test-backend-ops.cpp
+1,303 −0		tests/test-gguf.cpp