ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2024-12-18 20:27:57 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity

chore(llama.cpp): bump, drop penalize_nl (#4418)
Some checks are pending
Explorer deployment / build-linux (push) Waiting to run
Details
GPU tests / ubuntu-latest (1.21.x) (push) Waiting to run
Details
generate and publish GRPC docker caches / generate_caches (ubuntu:22.04, linux/amd64,linux/arm64, ubuntu-latest) (push) Waiting to run
Details
generate and publish intel docker caches / generate_caches (intel/oneapi-basekit:2025.0.0-0-devel-ubuntu22.04, linux/amd64, ubuntu-latest) (push) Waiting to run
Details
build container images / hipblas-jobs (-aio-gpu-hipblas, rocm/dev-ubuntu-22.04:6.1, hipblas, true, ubuntu:22.04, extras, latest-gpu-hipblas, latest-aio-gpu-hipblas, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -hipblas-ffmpeg) (push) Waiting to run
Details
build container images / hipblas-jobs (rocm/dev-ubuntu-22.04:6.1, hipblas, false, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -hipblas-core) (push) Waiting to run
Details
build container images / hipblas-jobs (rocm/dev-ubuntu-22.04:6.1, hipblas, false, ubuntu:22.04, extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -hipblas) (push) Waiting to run
Details
build container images / hipblas-jobs (rocm/dev-ubuntu-22.04:6.1, hipblas, true, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -hipblas-ffmpeg-core) (push) Waiting to run
Details
build container images / self-hosted-jobs (-aio-gpu-intel-f16, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, true, ubuntu:22.04, extras, latest-gpu-intel-f16, latest-aio-gpu-intel-f16, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -sycl-f16-ffmpeg) (push) Waiting to run
Details
build container images / self-hosted-jobs (-aio-gpu-intel-f32, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, true, ubuntu:22.04, extras, latest-gpu-intel-f32, latest-aio-gpu-intel-f32, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -sycl-f32-ffmpeg) (push) Waiting to run
Details
build container images / self-hosted-jobs (-aio-gpu-nvidia-cuda-11, ubuntu:22.04, cublas, 11, 7, true, extras, latest-gpu-nvidia-cuda-11, latest-aio-gpu-nvidia-cuda-11, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -cublas-cuda11-ffmpeg) (push) Waiting to run
Details
build container images / self-hosted-jobs (-aio-gpu-nvidia-cuda-12, ubuntu:22.04, cublas, 12, 0, true, extras, latest-gpu-nvidia-cuda-12, latest-aio-gpu-nvidia-cuda-12, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -cublas-cuda12-ffmpeg) (push) Waiting to run
Details
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, false, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f16-core) (push) Waiting to run
Details
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, true, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f16-ffmpeg-core) (push) Waiting to run
Details
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, false, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f32-core) (push) Waiting to run
Details
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, true, ubuntu:22.04, core, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f32-ffmpeg-core) (push) Waiting to run
Details
build container images / self-hosted-jobs (ubuntu:22.04, , , extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, ) (push) Waiting to run
Details
build container images / self-hosted-jobs (ubuntu:22.04, , true, extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -ffmpeg) (push) Waiting to run
Details
build container images / self-hosted-jobs (ubuntu:22.04, cublas, 11, 7, , extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda11) (push) Waiting to run
Details
build container images / self-hosted-jobs (ubuntu:22.04, cublas, 12, 0, , extras, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda12) (push) Waiting to run
Details
build container images / core-image-build (-aio-cpu, ubuntu:22.04, , true, core, latest-cpu, latest-aio-cpu, --jobs=4 --output-sync=target, linux/amd64,linux/arm64, arc-runner-set, auto, -ffmpeg-core) (push) Waiting to run
Details
build container images / core-image-build (ubuntu:22.04, cublas, 11, 7, , core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda11-core) (push) Waiting to run
Details
build container images / core-image-build (ubuntu:22.04, cublas, 11, 7, true, core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda11-ffmpeg-core) (push) Waiting to run
Details
build container images / core-image-build (ubuntu:22.04, cublas, 12, 0, , core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda12-core) (push) Waiting to run
Details
build container images / core-image-build (ubuntu:22.04, cublas, 12, 0, true, core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda12-ffmpeg-core) (push) Waiting to run
Details
build container images / core-image-build (ubuntu:22.04, vulkan, true, core, latest-vulkan-ffmpeg-core, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, -vulkan-ffmpeg-core) (push) Waiting to run
Details
Security Scan / tests (push) Waiting to run
Details
Tests extras backends / tests-transformers (push) Waiting to run
Details
Tests extras backends / tests-sentencetransformers (push) Waiting to run
Details
Tests extras backends / tests-rerankers (push) Waiting to run
Details
Tests extras backends / tests-diffusers (push) Waiting to run
Details
Tests extras backends / tests-parler-tts (push) Waiting to run
Details
Tests extras backends / tests-openvoice (push) Waiting to run
Details
Tests extras backends / tests-transformers-musicgen (push) Waiting to run
Details
Tests extras backends / tests-vallex (push) Waiting to run
Details
Tests extras backends / tests-coqui (push) Waiting to run
Details
tests / tests-linux (1.21.x) (push) Waiting to run
Details
tests / tests-aio-container (push) Waiting to run
Details
tests / tests-apple (1.21.x) (push) Waiting to run
Details

Browse Source 
deps(llama.cpp): bump, drop penalize_nl

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-12-17 00:47:52 +01:00 committed by GitHub
parent 24abf568cb
commit 708cba0c1b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Makefile
View File

@ -8,7 +8,7 @@ DETECT_LIBS?=true
# llama.cpp versions # llama.cpp versions
GOLLAMA_REPO?=https://github.com/go-skynet/go-llama.cpp GOLLAMA_REPO?=https://github.com/go-skynet/go-llama.cpp
GOLLAMA_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be GOLLAMA_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be
CPPLLAMA_VERSION?=a0974156f334acf8af5858d7ede5ab7d7490d415 CPPLLAMA_VERSION?=08ea539df211e46bb4d0dd275e541cb591d5ebc8
# whisper.cpp version # whisper.cpp version
WHISPER_REPO?=https://github.com/ggerganov/whisper.cpp WHISPER_REPO?=https://github.com/ggerganov/whisper.cpp

5
backend/cpp/llama/grpc-server.cpp
View File

@ -681,7 +681,6 @@ struct llama_server_context
slot->sparams.mirostat = json_value(data, "mirostat", default_sparams.mirostat); slot->sparams.mirostat = json_value(data, "mirostat", default_sparams.mirostat);
slot->sparams.mirostat_tau = json_value(data, "mirostat_tau", default_sparams.mirostat_tau); slot->sparams.mirostat_tau = json_value(data, "mirostat_tau", default_sparams.mirostat_tau);
slot->sparams.mirostat_eta = json_value(data, "mirostat_eta", default_sparams.mirostat_eta); slot->sparams.mirostat_eta = json_value(data, "mirostat_eta", default_sparams.mirostat_eta);
slot->sparams.penalize_nl = json_value(data, "penalize_nl", default_sparams.penalize_nl);
slot->params.n_keep = json_value(data, "n_keep", slot->params.n_keep); slot->params.n_keep = json_value(data, "n_keep", slot->params.n_keep);
slot->sparams.seed = json_value(data, "seed", default_sparams.seed); slot->sparams.seed = json_value(data, "seed", default_sparams.seed);
slot->sparams.grammar = json_value(data, "grammar", default_sparams.grammar); slot->sparams.grammar = json_value(data, "grammar", default_sparams.grammar);
@ -1213,7 +1212,6 @@ struct llama_server_context
{"mirostat", slot.sparams.mirostat}, {"mirostat", slot.sparams.mirostat},
{"mirostat_tau", slot.sparams.mirostat_tau}, {"mirostat_tau", slot.sparams.mirostat_tau},
{"mirostat_eta", slot.sparams.mirostat_eta}, {"mirostat_eta", slot.sparams.mirostat_eta},
{"penalize_nl", slot.sparams.penalize_nl},
{"stop", slot.params.antiprompt}, {"stop", slot.params.antiprompt},
{"n_predict", slot.params.n_predict}, {"n_predict", slot.params.n_predict},
{"n_keep", params.n_keep}, {"n_keep", params.n_keep},
@ -2112,7 +2110,6 @@ json parse_options(bool streaming, const backend::PredictOptions* predict, llama
// slot->sparams.mirostat = json_value(data, "mirostat", default_sparams.mirostat); // slot->sparams.mirostat = json_value(data, "mirostat", default_sparams.mirostat);
// slot->sparams.mirostat_tau = json_value(data, "mirostat_tau", default_sparams.mirostat_tau); // slot->sparams.mirostat_tau = json_value(data, "mirostat_tau", default_sparams.mirostat_tau);
// slot->sparams.mirostat_eta = json_value(data, "mirostat_eta", default_sparams.mirostat_eta); // slot->sparams.mirostat_eta = json_value(data, "mirostat_eta", default_sparams.mirostat_eta);
// slot->sparams.penalize_nl = json_value(data, "penalize_nl", default_sparams.penalize_nl);
// slot->params.n_keep = json_value(data, "n_keep", slot->params.n_keep); // slot->params.n_keep = json_value(data, "n_keep", slot->params.n_keep);
// slot->params.seed = json_value(data, "seed", default_params.seed); // slot->params.seed = json_value(data, "seed", default_params.seed);
// slot->sparams.grammar = json_value(data, "grammar", default_sparams.grammar); // slot->sparams.grammar = json_value(data, "grammar", default_sparams.grammar);
@ -2135,7 +2132,6 @@ json parse_options(bool streaming, const backend::PredictOptions* predict, llama
data["mirostat"] = predict->mirostat(); data["mirostat"] = predict->mirostat();
data["mirostat_tau"] = predict->mirostattau(); data["mirostat_tau"] = predict->mirostattau();
data["mirostat_eta"] = predict->mirostateta(); data["mirostat_eta"] = predict->mirostateta();
data["penalize_nl"] = predict->penalizenl();
data["n_keep"] = predict->nkeep(); data["n_keep"] = predict->nkeep();
data["seed"] = predict->seed(); data["seed"] = predict->seed();
data["grammar"] = predict->grammar(); data["grammar"] = predict->grammar();
@ -2181,7 +2177,6 @@ json parse_options(bool streaming, const backend::PredictOptions* predict, llama
// llama.params.sparams.mirostat = predict->mirostat(); // llama.params.sparams.mirostat = predict->mirostat();
// llama.params.sparams.mirostat_tau = predict->mirostattau(); // llama.params.sparams.mirostat_tau = predict->mirostattau();
// llama.params.sparams.mirostat_eta = predict->mirostateta(); // llama.params.sparams.mirostat_eta = predict->mirostateta();
// llama.params.sparams.penalize_nl = predict->penalizenl();
// llama.params.n_keep = predict->nkeep(); // llama.params.n_keep = predict->nkeep();
// llama.params.seed = predict->seed(); // llama.params.seed = predict->seed();
// llama.params.sparams.grammar = predict->grammar(); // llama.params.sparams.grammar = predict->grammar();