feat(llama.cpp): add reranking (#5396)
Some checks are pending
Explorer deployment / build-linux (push) Waiting to run
GPU tests / ubuntu-latest (1.21.x) (push) Waiting to run
generate and publish intel docker caches / generate_caches (intel/oneapi-basekit:2025.1.0-0-devel-ubuntu22.04, linux/amd64, ubuntu-latest) (push) Waiting to run
build container images / hipblas-jobs (-aio-gpu-hipblas, rocm/dev-ubuntu-22.04:6.1, hipblas, true, ubuntu:22.04, extras, latest-gpu-hipblas-extras, latest-aio-gpu-hipblas, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -hipblas-extras) (push) Waiting to run
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-extras, latest-aio-gpu-intel-f16, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f16-… (push) Waiting to run
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-extras, latest-aio-gpu-intel-f32, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f32-… (push) Waiting to run
build container images / hipblas-jobs (rocm/dev-ubuntu-22.04:6.1, hipblas, true, ubuntu:22.04, core, latest-gpu-hipblas, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -hipblas) (push) Waiting to run
build container images / self-hosted-jobs (-aio-gpu-nvidia-cuda-11, ubuntu:22.04, cublas, 11, 7, true, extras, latest-gpu-nvidia-cuda-11-extras, latest-aio-gpu-nvidia-cuda-11, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda11-extras) (push) Waiting to run
build container images / self-hosted-jobs (-aio-gpu-nvidia-cuda-12, ubuntu:22.04, cublas, 12, 0, true, extras, latest-gpu-nvidia-cuda-12-extras, latest-aio-gpu-nvidia-cuda-12, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda12-extras) (push) Waiting to run
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, true, ubuntu:22.04, core, latest-gpu-intel-f16, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f16) (push) Waiting to run
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, true, ubuntu:22.04, core, latest-gpu-intel-f32, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f32) (push) Waiting to run
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, false, auto, ) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, cublas, 11, 7, true, core, latest-gpu-nvidia-cuda-12, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda11) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, cublas, 12, 0, true, core, latest-gpu-nvidia-cuda-12, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda12) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, vulkan, true, core, latest-gpu-vulkan, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -vulkan) (push) Waiting to run
build container images / gh-runner (nvcr.io/nvidia/l4t-jetpack:r36.4.0, cublas, 12, 0, true, core, latest-nvidia-l4t-arm64, --jobs=4 --output-sync=target, linux/arm64, ubuntu-24.04-arm, true, false, -nvidia-l4t-arm64) (push) Waiting to run
Security Scan / tests (push) Waiting to run
Tests extras backends / tests-transformers (push) Waiting to run
Tests extras backends / tests-rerankers (push) Waiting to run
Tests extras backends / tests-diffusers (push) Waiting to run
Tests extras backends / tests-coqui (push) Waiting to run
tests / tests-linux (1.21.x) (push) Waiting to run
tests / tests-aio-container (push) Waiting to run
tests / tests-apple (1.21.x) (push) Waiting to run

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-05-22 21:49:30 +02:00 committed by GitHub
parent bac3022044
commit 3b0cf52f6a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 105 additions and 0 deletions

View file

@ -94,6 +94,11 @@ func grpcModelOpts(c config.BackendConfig) *pb.ModelOptions {
lowVRAM = *c.LowVRAM
}
reranking := false
if c.Reranking != nil {
reranking = *c.Reranking
}
mmap := false
if c.MMap != nil {
mmap = *c.MMap
@ -178,6 +183,7 @@ func grpcModelOpts(c config.BackendConfig) *pb.ModelOptions {
RopeFreqScale: c.RopeFreqScale,
NUMA: c.NUMA,
Embeddings: embeddings,
Reranking: reranking,
LowVRAM: lowVRAM,
NGPULayers: int32(nGPULayers),
MMap: mmap,

View file

@ -120,6 +120,7 @@ type LLMConfig struct {
MMap *bool `yaml:"mmap"`
MMlock *bool `yaml:"mmlock"`
LowVRAM *bool `yaml:"low_vram"`
Reranking *bool `yaml:"reranking"`
Grammar string `yaml:"grammar"`
StopWords []string `yaml:"stopwords"`
Cutstrings []string `yaml:"cutstrings"`
@ -372,6 +373,10 @@ func (cfg *BackendConfig) SetDefaults(opts ...ConfigLoaderOption) {
cfg.Embeddings = &falseV
}
if cfg.Reranking == nil {
cfg.Reranking = &falseV
}
if threads == 0 {
// Threads can't be 0
threads = 4