Merge pull request #155 from janhq/update-submodule-2024-07-22-17-05 · janhq/cortex.llamacpp@3bbdf8e

Commit

Merge pull request #155 from janhq/update-submodule-2024-07-22-17-05

Update llama.cpp submodule to latest release b3440

jan-service-account authored Jul 22, 2024

2 parents 12c45c1 + a60faf9 commit 3bbdf8e

+48 −33		convert_hf_to_gguf.py
+7 −6		convert_hf_to_gguf_update.py
+5 −1		convert_llama_ggml_to_gguf.py
+18 −8		convert_lora_to_gguf.py
+1 −1		examples/llama.android/llama/src/main/cpp/llama-android.cpp
+222 −137		examples/pydantic_models_to_grammar_examples.py
+1 −1		examples/server/README.md
+3 −3		flake.lock
+1 −1		ggml/src/ggml-quants.c
+26 −9		gguf-py/gguf/metadata.py
+3 −3		gguf-py/gguf/utility.py
+48 −3		gguf-py/tests/test_metadata.py
+1 −0		include/llama.h
+ −		models/ggml-vocab-gpt2.gguf
+ −		models/ggml-vocab-stablelm.gguf
+17 −22		src/llama.cpp
+14 −18		tests/CMakeLists.txt