From cc74fc93b4fddf17954a64bc718bfbffc9e9af4f Mon Sep 17 00:00:00 2001
From: Ettore Di Giacinto <mudler@users.noreply.github.com>
Date: Fri, 8 Sep 2023 18:38:22 +0200
Subject: [PATCH] feat(llama.cpp): update (#1024)

**Description**

This PR fixes #

**Notes for Reviewers**


**[Signed
commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)**
- [ ] Yes, I signed my commits.


<!--
Thank you for contributing to LocalAI!

Contributing Conventions:

1. Include descriptive PR titles with [<component-name>] prepended.
2. Build and test your changes before submitting a PR.
3. Sign your commits

By following the community's contribution conventions upfront, the
review process will
be accelerated and your PR merged more quickly.
-->

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---
 .env     | 18 ++++++++++++++++++
 Makefile |  8 ++++++--
 2 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/.env b/.env
index 4395e6c8ab1..ec53a8f43cf 100644
--- a/.env
+++ b/.env
@@ -23,6 +23,12 @@ MODELS_PATH=/models
 ## Enable debug mode
 # DEBUG=true
 
+## Disables COMPEL (Diffusers)
+# COMPEL=0
+
+## Enable/Disable single backend (useful if only one GPU is available)
+# SINGLE_ACTIVE_BACKEND=true
+
 ## Specify a build type. Available: cublas, openblas, clblas.
 ## cuBLAS: This is a GPU-accelerated version of the complete standard BLAS (Basic Linear Algebra Subprograms) library. It's provided by Nvidia and is part of their CUDA toolkit.
 ## OpenBLAS: This is an open-source implementation of the BLAS library that aims to provide highly optimized code for various platforms. It includes support for multi-threading and can be compiled to use hardware-specific features for additional performance. OpenBLAS can run on many kinds of hardware, including CPUs from Intel, AMD, and ARM.
@@ -44,3 +50,15 @@ MODELS_PATH=/models
 
 ## Specify a default upload limit in MB (whisper)
 # UPLOAD_LIMIT
+
+## List of external GRPC backends (note on the container image this variable is already set to use extra backends available in extra/)
+# EXTERNAL_GRPC_BACKENDS=my-backend:127.0.0.1:9000,my-backend2:/usr/bin/backend.py
+
+### Advanced settings ###
+### Those are not really used by LocalAI, but from components in the stack ###
+##
+### Preload libraries
+# LD_PRELOAD=
+
+### Huggingface cache for models
+# HUGGINGFACE_HUB_CACHE=/usr/local/huggingface
\ No newline at end of file
diff --git a/Makefile b/Makefile
index 2b941166066..910855928b5 100644
--- a/Makefile
+++ b/Makefile
@@ -4,7 +4,7 @@ GOVET=$(GOCMD) vet
 BINARY_NAME=local-ai
 
 # llama.cpp versions
-GOLLAMA_VERSION?=371ecd13c7fe00d281cb19c6588574134d7091b1
+GOLLAMA_VERSION?=05dc4b6210cde186ce47369fa0a8296390950851
 
 GOLLAMA_STABLE_VERSION?=50cee7712066d9e38306eccadcfbb44ea87df4b7
 
@@ -38,6 +38,7 @@ STABLEDIFFUSION_VERSION?=d89260f598afb809279bc72aa0107b4292587632
 GOGGLLM_VERSION?=862477d16eefb0805261c19c9b0d053e3b2b684b
 
 export BUILD_TYPE?=
+export CMAKE_ARGS?=
 CGO_LDFLAGS?=
 CUDA_LIBPATH?=/usr/local/cuda/lib64/
 GO_TAGS?=
@@ -64,9 +65,12 @@ ifndef UNAME_S
 UNAME_S := $(shell uname -s)
 endif
 
-# workaround for rwkv.cpp
 ifeq ($(UNAME_S),Darwin)
 	CGO_LDFLAGS += -lcblas -framework Accelerate
+ifneq ($(BUILD_TYPE),metal)
+    # explicit disable metal if on Darwin and metal is disabled
+	CMAKE_ARGS+=-DLLAMA_METAL=OFF
+endif
 endif
 
 ifeq ($(BUILD_TYPE),openblas)