vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge commit '280345968d' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/full-cuda.Dockerfile
#	.devops/llama-cpp-cuda.srpm.spec
#	.devops/main-cuda.Dockerfile
#	.devops/nix/package.nix
#	.devops/server-cuda.Dockerfile
#	.github/workflows/build.yml
#	CMakeLists.txt
#	Makefile
#	README.md
#	ci/run.sh
#	docs/token_generation_performance_tips.md
#	flake.lock
#	llama.cpp
#	scripts/LlamaConfig.cmake.in
#	scripts/compare-commits.sh
#	scripts/server-llm.sh
#	tests/test-quantize-fns.cpp
This commit is contained in:
Concedo 2024-04-07 20:27:17 +08:00
commit a530afa1e4
33 changed files with 124 additions and 1280 deletions
Download patch file Download diff file Expand all files Collapse all files

28
common/common.cpp
View file

@ -49,12 +49,12 @@
#pragma warning(disable: 4244 4267) // possible loss of data
#endif
#if (defined(GGML_USE_CUBLAS) || defined(GGML_USE_SYCL))
#define GGML_USE_CUBLAS_SYCL
#if (defined(GGML_USE_CUDA) || defined(GGML_USE_SYCL))
#define GGML_USE_CUDA_SYCL
#endif
#if (defined(GGML_USE_CUBLAS) || defined(GGML_USE_SYCL)) || defined(GGML_USE_VULKAN)
#define GGML_USE_CUBLAS_SYCL_VULKAN
#if (defined(GGML_USE_CUDA) || defined(GGML_USE_SYCL)) || defined(GGML_USE_VULKAN)
#define GGML_USE_CUDA_SYCL_VULKAN
#endif
#if defined(LLAMA_USE_CURL)
@ -862,9 +862,9 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
return true;
}
params.main_gpu = std::stoi(argv[i]);
#ifndef GGML_USE_CUBLAS_SYCL
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS/SYCL. Setting the main GPU has no effect.\n");
#endif // GGML_USE_CUBLAS_SYCL
#ifndef GGML_USE_CUDA_SYCL
fprintf(stderr, "warning: llama.cpp was compiled without CUDA/SYCL. Setting the main GPU has no effect.\n");
#endif // GGML_USE_CUDA_SYCL
return true;
}
if (arg == "--split-mode" || arg == "-sm") {
@ -890,9 +890,9 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
invalid_param = true;
return true;
}
#ifndef GGML_USE_CUBLAS_SYCL
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS/SYCL. Setting the split mode has no effect.\n");
#endif // GGML_USE_CUBLAS_SYCL
#ifndef GGML_USE_CUDA_SYCL
fprintf(stderr, "warning: llama.cpp was compiled without CUDA/SYCL. Setting the split mode has no effect.\n");
#endif // GGML_USE_CUDA_SYCL
return true;
}
if (arg == "--tensor-split" || arg == "-ts") {
@ -918,9 +918,9 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
params.tensor_split[i] = 0.0f;
}
}
#ifndef GGML_USE_CUBLAS_SYCL_VULKAN
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS/SYCL/Vulkan. Setting a tensor split has no effect.\n");
#endif // GGML_USE_CUBLAS_SYCL
#ifndef GGML_USE_CUDA_SYCL_VULKAN
fprintf(stderr, "warning: llama.cpp was compiled without CUDA/SYCL/Vulkan. Setting a tensor split has no effect.\n");
#endif // GGML_USE_CUDA_SYCL_VULKAN
return true;
}
if (arg == "--no-mmap") {
@ -2388,7 +2388,7 @@ void dump_non_result_info_yaml(FILE * stream, const gpt_params & params, const l
fprintf(stream, "cpu_has_avx512: %s\n", ggml_cpu_has_avx512() ? "true" : "false");
fprintf(stream, "cpu_has_avx512_vbmi: %s\n", ggml_cpu_has_avx512_vbmi() ? "true" : "false");
fprintf(stream, "cpu_has_avx512_vnni: %s\n", ggml_cpu_has_avx512_vnni() ? "true" : "false");
fprintf(stream, "cpu_has_cublas: %s\n", ggml_cpu_has_cublas() ? "true" : "false");
fprintf(stream, "cpu_has_cuda: %s\n", ggml_cpu_has_cuda() ? "true" : "false");
fprintf(stream, "cpu_has_vulkan: %s\n", ggml_cpu_has_vulkan() ? "true" : "false");
fprintf(stream, "cpu_has_clblast: %s\n", ggml_cpu_has_clblast() ? "true" : "false");
fprintf(stream, "cpu_has_kompute: %s\n", ggml_cpu_has_kompute() ? "true" : "false");