Skip to content

Commit 3db5058

Browse files
author
jaime-m-p
committed
Merge branch 'master' into tokenizer-fixes
2 parents 9b8e05b + 57b1d4f commit 3db5058

File tree

127 files changed

+15831
-147908
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

127 files changed

+15831
-147908
lines changed

‎.devops/full-cuda.Dockerfile

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ ARG CUDA_VERSION=11.7.1
66
# Target the CUDA build image
77
ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
88

9-
FROM ${BASE_CUDA_DEV_CONTAINER} as build
9+
FROM ${BASE_CUDA_DEV_CONTAINER} AS build
1010

1111
# Unless otherwise specified, we make a fat build.
1212
ARG CUDA_DOCKER_ARCH=all

‎.devops/full-rocm.Dockerfile

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ ARG ROCM_VERSION=5.6
66
# Target the CUDA build image
77
ARG BASE_ROCM_DEV_CONTAINER=rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION}-complete
88

9-
FROM ${BASE_ROCM_DEV_CONTAINER} as build
9+
FROM ${BASE_ROCM_DEV_CONTAINER} AS build
1010

1111
# Unless otherwise specified, we make a fat build.
1212
# List from https://github.com/ggerganov/llama.cpp/pull/1087#issuecomment-1682807878

‎.devops/full.Dockerfile

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
ARG UBUNTU_VERSION=22.04
22

3-
FROM ubuntu:$UBUNTU_VERSION as build
3+
FROM ubuntu:$UBUNTU_VERSION AS build
44

55
RUN apt-get update && \
66
apt-get install -y build-essential python3 python3-pip git libcurl4-openssl-dev libgomp1

‎.devops/llama-cli-cuda.Dockerfile

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VER
66
# Target the CUDA runtime image
77
ARG BASE_CUDA_RUN_CONTAINER=nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
88

9-
FROM ${BASE_CUDA_DEV_CONTAINER} as build
9+
FROM ${BASE_CUDA_DEV_CONTAINER} AS build
1010

1111
# Unless otherwise specified, we make a fat build.
1212
ARG CUDA_DOCKER_ARCH=all
@@ -25,7 +25,7 @@ ENV GGML_CUDA=1
2525

2626
RUN make -j$(nproc) llama-cli
2727

28-
FROM ${BASE_CUDA_RUN_CONTAINER} as runtime
28+
FROM ${BASE_CUDA_RUN_CONTAINER} AS runtime
2929

3030
RUN apt-get update && \
3131
apt-get install -y libgomp1

‎.devops/llama-cli-intel.Dockerfile

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
ARG ONEAPI_VERSION=2024.1.1-devel-ubuntu22.04
22

3-
FROM intel/oneapi-basekit:$ONEAPI_VERSION as build
3+
FROM intel/oneapi-basekit:$ONEAPI_VERSION AS build
44

55
ARG GGML_SYCL_F16=OFF
66
RUN apt-get update && \
@@ -17,7 +17,7 @@ RUN if [ "${GGML_SYCL_F16}" = "ON" ]; then \
1717
cmake -B build -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx ${OPT_SYCL_F16} && \
1818
cmake --build build --config Release --target llama-cli
1919

20-
FROM intel/oneapi-basekit:$ONEAPI_VERSION as runtime
20+
FROM intel/oneapi-basekit:$ONEAPI_VERSION AS runtime
2121

2222
COPY --from=build /app/build/bin/llama-cli /llama-cli
2323

‎.devops/llama-cli-rocm.Dockerfile

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ ARG ROCM_VERSION=5.6
66
# Target the CUDA build image
77
ARG BASE_ROCM_DEV_CONTAINER=rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION}-complete
88

9-
FROM ${BASE_ROCM_DEV_CONTAINER} as build
9+
FROM ${BASE_ROCM_DEV_CONTAINER} AS build
1010

1111
# Unless otherwise specified, we make a fat build.
1212
# List from https://github.com/ggerganov/llama.cpp/pull/1087#issuecomment-1682807878

‎.devops/llama-cli-vulkan.Dockerfile

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
ARG UBUNTU_VERSION=jammy
22

3-
FROM ubuntu:$UBUNTU_VERSION as build
3+
FROM ubuntu:$UBUNTU_VERSION AS build
44

55
# Install build tools
66
RUN apt update && apt install -y git build-essential cmake wget libgomp1

‎.devops/llama-cli.Dockerfile

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
ARG UBUNTU_VERSION=22.04
22

3-
FROM ubuntu:$UBUNTU_VERSION as build
3+
FROM ubuntu:$UBUNTU_VERSION AS build
44

55
RUN apt-get update && \
66
apt-get install -y build-essential git
@@ -11,7 +11,7 @@ COPY . .
1111

1212
RUN make -j$(nproc) llama-cli
1313

14-
FROM ubuntu:$UBUNTU_VERSION as runtime
14+
FROM ubuntu:$UBUNTU_VERSION AS runtime
1515

1616
RUN apt-get update && \
1717
apt-get install -y libgomp1

‎.devops/llama-server-cuda.Dockerfile

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VER
66
# Target the CUDA runtime image
77
ARG BASE_CUDA_RUN_CONTAINER=nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
88

9-
FROM ${BASE_CUDA_DEV_CONTAINER} as build
9+
FROM ${BASE_CUDA_DEV_CONTAINER} AS build
1010

1111
# Unless otherwise specified, we make a fat build.
1212
ARG CUDA_DOCKER_ARCH=all
@@ -27,7 +27,7 @@ ENV LLAMA_CURL=1
2727

2828
RUN make -j$(nproc) llama-server
2929

30-
FROM ${BASE_CUDA_RUN_CONTAINER} as runtime
30+
FROM ${BASE_CUDA_RUN_CONTAINER} AS runtime
3131

3232
RUN apt-get update && \
3333
apt-get install -y libcurl4-openssl-dev libgomp1 curl

‎.devops/llama-server-intel.Dockerfile

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
ARG ONEAPI_VERSION=2024.1.1-devel-ubuntu22.04
22

3-
FROM intel/oneapi-basekit:$ONEAPI_VERSION as build
3+
FROM intel/oneapi-basekit:$ONEAPI_VERSION AS build
44

55
ARG GGML_SYCL_F16=OFF
66
RUN apt-get update && \
@@ -17,7 +17,7 @@ RUN if [ "${GGML_SYCL_F16}" = "ON" ]; then \
1717
cmake -B build -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_CURL=ON ${OPT_SYCL_F16} && \
1818
cmake --build build --config Release --target llama-server
1919

20-
FROM intel/oneapi-basekit:$ONEAPI_VERSION as runtime
20+
FROM intel/oneapi-basekit:$ONEAPI_VERSION AS runtime
2121

2222
RUN apt-get update && \
2323
apt-get install -y libcurl4-openssl-dev curl

‎.devops/llama-server-rocm.Dockerfile

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ ARG ROCM_VERSION=5.6
66
# Target the CUDA build image
77
ARG BASE_ROCM_DEV_CONTAINER=rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION}-complete
88

9-
FROM ${BASE_ROCM_DEV_CONTAINER} as build
9+
FROM ${BASE_ROCM_DEV_CONTAINER} AS build
1010

1111
# Unless otherwise specified, we make a fat build.
1212
# List from https://github.com/ggerganov/llama.cpp/pull/1087#issuecomment-1682807878

‎.devops/llama-server-vulkan.Dockerfile

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
ARG UBUNTU_VERSION=jammy
22

3-
FROM ubuntu:$UBUNTU_VERSION as build
3+
FROM ubuntu:$UBUNTU_VERSION AS build
44

55
# Install build tools
66
RUN apt update && apt install -y git build-essential cmake wget

‎.devops/llama-server.Dockerfile

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
ARG UBUNTU_VERSION=22.04
22

3-
FROM ubuntu:$UBUNTU_VERSION as build
3+
FROM ubuntu:$UBUNTU_VERSION AS build
44

55
RUN apt-get update && \
66
apt-get install -y build-essential git libcurl4-openssl-dev curl
@@ -13,7 +13,7 @@ ENV LLAMA_CURL=1
1313

1414
RUN make -j$(nproc) llama-server
1515

16-
FROM ubuntu:$UBUNTU_VERSION as runtime
16+
FROM ubuntu:$UBUNTU_VERSION AS runtime
1717

1818
RUN apt-get update && \
1919
apt-get install -y libcurl4-openssl-dev libgomp1

‎.devops/nix/package.nix

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -18,6 +18,7 @@
1818
vulkan-headers,
1919
vulkan-loader,
2020
curl,
21+
shaderc,
2122
useBlas ? builtins.all (x: !x) [
2223
useCuda
2324
useMetalKit
@@ -146,6 +147,7 @@ let
146147
vulkanBuildInputs = [
147148
vulkan-headers
148149
vulkan-loader
150+
shaderc
149151
];
150152
in
151153

‎.devops/tools.sh

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,7 @@ arg1="$1"
88
shift
99

1010
if [[ "$arg1" == '--convert' || "$arg1" == '-c' ]]; then
11-
python3 ./convert-hf-to-gguf.py "$@"
11+
python3 ./convert_hf_to_gguf.py "$@"
1212
elif [[ "$arg1" == '--quantize' || "$arg1" == '-q' ]]; then
1313
./llama-quantize "$@"
1414
elif [[ "$arg1" == '--run' || "$arg1" == '-r' ]]; then

‎.github/workflows/build.yml

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -355,8 +355,10 @@ jobs:
355355
- name: Dependencies
356356
id: depends
357357
run: |
358-
sudo apt-get update
359-
sudo apt-get install build-essential libvulkan-dev
358+
wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | sudo apt-key add -
359+
sudo wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list
360+
sudo apt-get update -y
361+
sudo apt-get install -y build-essential vulkan-sdk
360362
361363
- name: Build
362364
id: cmake_build

‎.gitignore

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -61,6 +61,11 @@ llama-batched-swift
6161
out/
6262
tmp/
6363

64+
# Deprecated
65+
66+
/main
67+
/server
68+
6469
# CI
6570

6671
!.github/workflows/*.yml

‎CMakeLists.txt

Lines changed: 11 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -106,6 +106,7 @@ llama_option_depr(WARNING LLAMA_NATIVE GGML_NATIVE)
106106
llama_option_depr(WARNING LLAMA_RPC GGML_RPC)
107107
llama_option_depr(WARNING LLAMA_SYCL GGML_SYCL)
108108
llama_option_depr(WARNING LLAMA_SYCL_F16 GGML_SYCL_F16)
109+
llama_option_depr(WARNING LLAMA_CANN GGML_CANN)
109110

110111
#
111112
# build the library
@@ -132,7 +133,16 @@ set(LLAMA_INCLUDE_INSTALL_DIR ${CMAKE_INSTALL_INCLUDEDIR} CACHE PATH "Location o
132133
set(LLAMA_LIB_INSTALL_DIR ${CMAKE_INSTALL_LIBDIR} CACHE PATH "Location of library files")
133134
set(LLAMA_BIN_INSTALL_DIR ${CMAKE_INSTALL_BINDIR} CACHE PATH "Location of binary files")
134135

135-
get_directory_property(LLAMA_TRANSIENT_DEFINES COMPILE_DEFINITIONS)
136+
137+
# At the moment some compile definitions are placed within the ggml/src
138+
# directory but not exported on the `ggml` target. This could be improved by
139+
# determining _precisely_ which defines are necessary for the llama-config
140+
# package.
141+
#
142+
get_directory_property(GGML_DIR_DEFINES DIRECTORY ggml/src COMPILE_DEFINITIONS)
143+
get_target_property(GGML_TARGET_DEFINES ggml COMPILE_DEFINITIONS)
144+
set(GGML_TRANSIENT_DEFINES ${GGML_TARGET_DEFINES} ${GGML_DIR_DEFINES})
145+
get_target_property(GGML_LINK_LIBRARIES ggml LINK_LIBRARIES)
136146

137147
set_target_properties(llama PROPERTIES PUBLIC_HEADER ${CMAKE_CURRENT_SOURCE_DIR}/include/llama.h)
138148
install(TARGETS llama LIBRARY PUBLIC_HEADER)

‎CONTRIBUTING.md

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,6 @@
55
- Test your changes:
66
- Using the commands in the [`tests`](tests) folder. For instance, running the `./tests/test-backend-ops` command tests different backend implementations of the GGML library
77
- Execute [the full CI locally on your machine](ci/README.md) before publishing
8-
- If the pull request contains only documentation changes (e.g., updating READMEs, adding new wiki pages), please add `[no ci]` to the commit title. This will skip unnecessary CI checks and help reduce build times
98
- Please rate the complexity of your PR (i.e. `Review Complexity : Low`, `Review Complexity : Medium`, `Review Complexity : High`). This makes it easier for maintainers to triage the PRs.
109
- The PR template has a series of review complexity checkboxes `[ ]` that [you can mark as](https://docs.github.com/en/get-started/writing-on-github/working-with-advanced-formatting/about-task-lists) `[X]` for your conveience
1110

‎Makefile

Lines changed: 52 additions & 23 deletions
Original file line numberDiff line numberDiff line change
@@ -197,6 +197,10 @@ ifdef GGML_RPC
197197
BUILD_TARGETS += rpc-server
198198
endif
199199

200+
ifdef GGML_VULKAN
201+
BUILD_TARGETS += vulkan-shaders-gen
202+
endif
203+
200204
default: $(BUILD_TARGETS) $(LEGACY_TARGETS_BUILD)
201205

202206
test: $(TEST_TARGETS)
@@ -547,11 +551,17 @@ ifdef GGML_OPENBLAS64
547551
endif # GGML_OPENBLAS64
548552

549553
ifdef GGML_BLIS
550-
MK_CPPFLAGS += -DGGML_USE_BLAS -I/usr/local/include/blis -I/usr/include/blis
554+
MK_CPPFLAGS += -DGGML_USE_BLAS -DGGML_BLAS_USE_BLIS -I/usr/local/include/blis -I/usr/include/blis
551555
MK_LDFLAGS += -lblis -L/usr/local/lib
552556
OBJ_GGML += ggml/src/ggml-blas.o
553557
endif # GGML_BLIS
554558

559+
ifdef GGML_NVPL
560+
MK_CPPFLAGS += -DGGML_USE_BLAS -DGGML_BLAS_USE_NVPL -DNVPL_ILP64 -I/usr/local/include/nvpl_blas -I/usr/include/nvpl_blas
561+
MK_LDFLAGS += -L/usr/local/lib -lnvpl_blas_core -lnvpl_blas_ilp64_gomp
562+
OBJ_GGML += ggml/src/ggml-blas.o
563+
endif # GGML_NVPL
564+
555565
ifndef GGML_NO_LLAMAFILE
556566
MK_CPPFLAGS += -DGGML_USE_LLAMAFILE
557567
OBJ_GGML += ggml/src/llamafile/sgemm.o
@@ -704,8 +714,8 @@ endif # GGML_CUDA
704714

705715
ifdef GGML_VULKAN
706716
MK_CPPFLAGS += -DGGML_USE_VULKAN
707-
MK_LDFLAGS += -lvulkan
708-
OBJ_GGML += ggml/src/ggml-vulkan.o
717+
MK_LDFLAGS += $(shell pkg-config --libs vulkan)
718+
OBJ_GGML += ggml/src/ggml-vulkan.o ggml/src/ggml-vulkan-shaders.o
709719

710720
ifdef GGML_VULKAN_CHECK_RESULTS
711721
MK_CPPFLAGS += -DGGML_VULKAN_CHECK_RESULTS
@@ -727,10 +737,28 @@ ifdef GGML_VULKAN_RUN_TESTS
727737
MK_CPPFLAGS += -DGGML_VULKAN_RUN_TESTS
728738
endif
729739

730-
ggml/src/ggml-vulkan.o: \
731-
ggml/src/ggml-vulkan.cpp \
732-
ggml/include/ggml-vulkan.h
733-
$(CXX) $(CXXFLAGS) -c $< -o $@
740+
GLSLC_CMD = glslc
741+
_ggml_vk_genshaders_cmd = $(shell pwd)/vulkan-shaders-gen
742+
_ggml_vk_header = ggml/src/ggml-vulkan-shaders.hpp
743+
_ggml_vk_source = ggml/src/ggml-vulkan-shaders.cpp
744+
_ggml_vk_input_dir = ggml/src/vulkan-shaders
745+
_ggml_vk_shader_deps = $(echo $(_ggml_vk_input_dir)/*.comp)
746+
747+
ggml/src/ggml-vulkan.o: ggml/src/ggml-vulkan.cpp ggml/include/ggml-vulkan.h $(_ggml_vk_header) $(_ggml_vk_source)
748+
$(CXX) $(CXXFLAGS) $(shell pkg-config --cflags vulkan) -c $< -o $@
749+
750+
$(_ggml_vk_header): $(_ggml_vk_source)
751+
752+
$(_ggml_vk_source): $(_ggml_vk_shader_deps) vulkan-shaders-gen
753+
$(_ggml_vk_genshaders_cmd) \
754+
--glslc $(GLSLC_CMD) \
755+
--input-dir $(_ggml_vk_input_dir) \
756+
--target-hpp $(_ggml_vk_header) \
757+
--target-cpp $(_ggml_vk_source)
758+
759+
vulkan-shaders-gen: ggml/src/vulkan-shaders/vulkan-shaders-gen.cpp
760+
$(CXX) $(CXXFLAGS) -o $@ $(LDFLAGS) ggml/src/vulkan-shaders/vulkan-shaders-gen.cpp
761+
734762
endif # GGML_VULKAN
735763

736764
ifdef GGML_HIPBLAS
@@ -767,6 +795,14 @@ ifdef GGML_CUDA_FORCE_DMMV
767795
HIPFLAGS += -DGGML_CUDA_FORCE_DMMV
768796
endif # GGML_CUDA_FORCE_DMMV
769797

798+
ifdef GGML_CUDA_FORCE_MMQ
799+
HIPFLAGS += -DGGML_CUDA_FORCE_MMQ
800+
endif # GGML_CUDA_FORCE_MMQ
801+
802+
ifdef GGML_CUDA_FORCE_CUBLAS
803+
HIPFLAGS += -DGGML_CUDA_FORCE_CUBLAS
804+
endif # GGML_CUDA_FORCE_CUBLAS
805+
770806
ifdef GGML_CUDA_NO_PEER_COPY
771807
HIPFLAGS += -DGGML_CUDA_NO_PEER_COPY
772808
endif # GGML_CUDA_NO_PEER_COPY
@@ -1110,6 +1146,7 @@ clean:
11101146
rm -vrf ggml/src/ggml-cuda/template-instances/*.o
11111147
rm -rvf $(BUILD_TARGETS)
11121148
rm -rvf $(TEST_TARGETS)
1149+
rm -f vulkan-shaders-gen ggml/src/ggml-vulkan-shaders.hpp ggml/src/ggml-vulkan-shaders.cpp
11131150
rm -rvf $(LEGACY_TARGETS_CLEAN)
11141151
find examples pocs -type f -name "*.o" -delete
11151152

@@ -1513,15 +1550,17 @@ llama-q8dot: pocs/vdot/q8dot.cpp ggml/src/ggml.o \
15131550
# Mark legacy binary targets as .PHONY so that they are always checked.
15141551
.PHONY: main quantize perplexity embedding server finetune
15151552

1553+
# NOTE: We currently will always build the deprecation-warning `main` and `server` binaries to help users migrate.
1554+
# Eventually we will want to remove these target from building all the time.
15161555
main: examples/deprecation-warning/deprecation-warning.cpp
1517-
ifneq (,$(wildcard main))
15181556
$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
15191557
$(CXX) $(CXXFLAGS) $(filter-out $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
1520-
@echo "#########"
1521-
@echo "WARNING: The 'main' binary is deprecated. Please use 'llama-cli' instead."
1522-
@echo " Remove the 'main' binary to remove this warning."
1523-
@echo "#########"
1524-
endif
1558+
@echo "NOTICE: The 'main' binary is deprecated. Please use 'llama-cli' instead."
1559+
1560+
server: examples/deprecation-warning/deprecation-warning.cpp
1561+
$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
1562+
$(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
1563+
@echo "NOTICE: The 'server' binary is deprecated. Please use 'llama-server' instead."
15251564

15261565
quantize: examples/deprecation-warning/deprecation-warning.cpp
15271566
ifneq (,$(wildcard quantize))
@@ -1553,16 +1592,6 @@ ifneq (,$(wildcard embedding))
15531592
@echo "#########"
15541593
endif
15551594

1556-
server: examples/deprecation-warning/deprecation-warning.cpp
1557-
ifneq (,$(wildcard server))
1558-
$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
1559-
$(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
1560-
@echo "#########"
1561-
@echo "WARNING: The 'server' binary is deprecated. Please use 'llama-server' instead."
1562-
@echo " Remove the 'server' binary to remove this warning."
1563-
@echo "#########"
1564-
endif
1565-
15661595
finetune: examples/deprecation-warning/deprecation-warning.cpp
15671596
ifneq (,$(wildcard finetune))
15681597
$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)

‎README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@
33
![llama](https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png)
44

55
[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://opensource.org/licenses/MIT)
6-
[![Server](https://github.com/ggerganov/llama.cpp/actions/workflows/server.yml/badge.svg?branch=master&event=schedule)](https://github.com/ggerganov/llama.cpp/actions/workflows/server.yml)
6+
[![Server](https://github.com/ggerganov/llama.cpp/actions/workflows/server.yml/badge.svg)](https://github.com/ggerganov/llama.cpp/actions/workflows/server.yml)
77
[![Conan Center](https://shields.io/conan/v/llama-cpp)](https://conan.io/center/llama-cpp)
88

99
[Roadmap](https://github.com/users/ggerganov/projects/7) / [Project status](https://github.com/ggerganov/llama.cpp/discussions/3471) / [Manifesto](https://github.com/ggerganov/llama.cpp/discussions/205) / [ggml](https://github.com/ggerganov/ggml)

0 commit comments

Comments
 (0)