From ff99a1fa704438f9c4bcca3c6d3b3192b6e5e300 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Fri, 30 Aug 2024 23:30:37 +0200 Subject: [PATCH] chore(deps): update llama.cpp Signed-off-by: Ettore Di Giacinto --- Makefile | 2 +- backend/cpp/llama/grpc-server.cpp | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/Makefile b/Makefile index 69bb3aa6bdb3..9e3cdd43d106 100644 --- a/Makefile +++ b/Makefile @@ -8,7 +8,7 @@ DETECT_LIBS?=true # llama.cpp versions GOLLAMA_REPO?=https://github.com/go-skynet/go-llama.cpp GOLLAMA_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be -CPPLLAMA_VERSION?=9fe94ccac92693d4ae1bc283ff0574e8b3f4e765 +CPPLLAMA_VERSION?=0ab30f8d82fc7156b750c194d64a887e80cbfb82 # go-rwkv version RWKV_REPO?=https://github.com/donomii/go-rwkv.cpp diff --git a/backend/cpp/llama/grpc-server.cpp b/backend/cpp/llama/grpc-server.cpp index 57ab46fe6a42..e1b6f868b2e8 100644 --- a/backend/cpp/llama/grpc-server.cpp +++ b/backend/cpp/llama/grpc-server.cpp @@ -1119,7 +1119,7 @@ struct llama_server_context continue; } - if (!llava_image_embed_make_with_clip_img(clp_ctx, params.n_threads, img.img_data, &img.image_embedding, &img.image_tokens)) { + if (!llava_image_embed_make_with_clip_img(clp_ctx, params.cpuparams.n_threads, img.img_data, &img.image_embedding, &img.image_tokens)) { LOG_TEE("Error processing the given image"); return false; } @@ -2210,7 +2210,7 @@ static void params_parse(const backend::ModelOptions* request, params.model_alias = request->modelfile(); params.n_ctx = request->contextsize(); //params.memory_f16 = request->f16memory(); - params.n_threads = request->threads(); + params.cpuparams.n_threads = request->threads(); params.n_gpu_layers = request->ngpulayers(); params.n_batch = request->nbatch(); // Set params.n_parallel by environment variable (LLAMA_PARALLEL), defaults to 1