From ed954d66c3b9c901b58277c24931661a3d43a1f7 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Fri, 21 Apr 2023 00:55:19 +0200 Subject: [PATCH] Do not take all CPU by default (#50) --- README.md | 2 +- go.mod | 10 ++++++++++ go.sum | 27 +++++++++++++++++++++++++++ main.go | 11 ++++++++--- 4 files changed, 46 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index afbec65..330b3ec 100644 --- a/README.md +++ b/README.md @@ -117,7 +117,7 @@ The API takes takes the following parameters: | Parameter | Environment Variable | Default Value | Description | | ------------ | -------------------- | ------------- | -------------------------------------- | | models-path | MODELS_PATH | | The path where you have models (ending with `.bin`). | -| threads | THREADS | CPU cores | The number of threads to use for text generation. | +| threads | THREADS | Number of Physical cores | The number of threads to use for text generation. | | address | ADDRESS | :8080 | The address and port to listen on. | | context-size | CONTEXT_SIZE | 512 | Default token context size. | diff --git a/go.mod b/go.mod index d90137b..e65ef28 100644 --- a/go.mod +++ b/go.mod @@ -7,19 +7,27 @@ require ( github.com/go-skynet/go-gpt4all-j.cpp v0.0.0-20230419091210-303cf2a59a94 github.com/go-skynet/go-llama.cpp v0.0.0-20230415213228-bac222030640 github.com/gofiber/fiber/v2 v2.42.0 + github.com/jaypipes/ghw v0.10.0 github.com/rs/zerolog v1.29.1 github.com/urfave/cli/v2 v2.25.0 ) require ( + github.com/StackExchange/wmi v1.2.1 // indirect github.com/andybalholm/brotli v1.0.4 // indirect github.com/cpuguy83/go-md2man/v2 v2.0.2 // indirect + github.com/ghodss/yaml v1.0.0 // indirect + github.com/go-ole/go-ole v1.2.6 // indirect github.com/google/uuid v1.3.0 // indirect + github.com/jaypipes/pcidb v1.0.0 // indirect github.com/klauspost/compress v1.15.9 // indirect + github.com/kr/text v0.2.0 // indirect github.com/mattn/go-colorable v0.1.13 // indirect github.com/mattn/go-isatty v0.0.17 // indirect github.com/mattn/go-runewidth v0.0.14 // indirect + github.com/mitchellh/go-homedir v1.1.0 // indirect github.com/philhofer/fwd v1.1.1 // indirect + github.com/pkg/errors v0.9.1 // indirect github.com/rivo/uniseg v0.2.0 // indirect github.com/russross/blackfriday/v2 v2.1.0 // indirect github.com/savsgio/dictpool v0.0.0-20221023140959-7bf2e61cea94 // indirect @@ -30,4 +38,6 @@ require ( github.com/valyala/tcplisten v1.0.0 // indirect github.com/xrash/smetrics v0.0.0-20201216005158-039620a65673 // indirect golang.org/x/sys v0.6.0 // indirect + gopkg.in/yaml.v2 v2.4.0 // indirect + howett.net/plist v1.0.0 // indirect ) diff --git a/go.sum b/go.sum index 880540b..0218734 100644 --- a/go.sum +++ b/go.sum @@ -1,9 +1,17 @@ +github.com/StackExchange/wmi v1.2.1 h1:VIkavFPXSjcnS+O8yTq7NI32k0R5Aj+v39y29VYDOSA= +github.com/StackExchange/wmi v1.2.1/go.mod h1:rcmrprowKIVzvc+NUiLncP2uuArMWLCbu9SBzvHz7e8= github.com/andybalholm/brotli v1.0.4 h1:V7DdXeJtZscaqfNuAdSRuRFzuiKlHSC/Zh3zl9qY3JY= github.com/andybalholm/brotli v1.0.4/go.mod h1:fO7iG3H7G2nSZ7m0zPUDn85XEX2GTukHGRSepvi9Eig= github.com/coreos/go-systemd/v22 v22.5.0/go.mod h1:Y58oyj3AT4RCenI/lSvhwexgC+NSVTIJ3seZv2GcEnc= github.com/cpuguy83/go-md2man/v2 v2.0.2 h1:p1EgwI/C7NhT0JmVkwCD2ZBK8j4aeHQX2pMHHBfMQ6w= github.com/cpuguy83/go-md2man/v2 v2.0.2/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o= +github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E= +github.com/ghodss/yaml v1.0.0 h1:wQHKEahhL6wmXdzwWG11gIVCkOv05bNOh+Rxn0yngAk= +github.com/ghodss/yaml v1.0.0/go.mod h1:4dBDuWmgqj2HViK6kFavaiC9ZROes6MMH2rRYeMEF04= github.com/go-logr/logr v1.2.3 h1:2DntVwHkVopvECVRSlL5PSo9eG+cAkDCuckLubN+rq0= +github.com/go-ole/go-ole v1.2.5/go.mod h1:pprOEPIfldk/42T2oK7lQ4v4JSDwmV0As9GaiUsvbm0= +github.com/go-ole/go-ole v1.2.6 h1:/Fpf6oFPoeFik9ty7siob0G6Ke8QvQEuVcuChpwXzpY= +github.com/go-ole/go-ole v1.2.6/go.mod h1:pprOEPIfldk/42T2oK7lQ4v4JSDwmV0As9GaiUsvbm0= github.com/go-skynet/go-gpt2.cpp v0.0.0-20230420213900-1c24f5b86ac4 h1:GkGuqnhDFKlCsT6Bo8sdY00A7rFXCzfU1nBOSS4ZnYM= github.com/go-skynet/go-gpt2.cpp v0.0.0-20230420213900-1c24f5b86ac4/go.mod h1:1Wj/xbkMfwQSOrhNYK178IzqQHstZbRfhx4s8p1M5VM= github.com/go-skynet/go-gpt4all-j.cpp v0.0.0-20230419091210-303cf2a59a94 h1:rtrrMvlIq+g0/ltXjDdLeNtz0uc4wJ4Qs15GFU4ba4c= @@ -18,8 +26,16 @@ github.com/google/go-cmp v0.5.9 h1:O2Tfq5qg4qc4AmwVlvv0oLiVAGB7enBSJ2x2DqQFi38= github.com/google/pprof v0.0.0-20210407192527-94a9f03dee38 h1:yAJXTCF9TqKcTiHJAE8dj7HMvPfh66eeA2JYW7eFpSE= github.com/google/uuid v1.3.0 h1:t6JiXgmwXMjEs8VusXIJk2BXHsn+wx8BZdTaoZ5fu7I= github.com/google/uuid v1.3.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo= +github.com/jaypipes/ghw v0.10.0 h1:UHu9UX08Py315iPojADFPOkmjTsNzHj4g4adsNKKteY= +github.com/jaypipes/ghw v0.10.0/go.mod h1:jeJGbkRB2lL3/gxYzNYzEDETV1ZJ56OKr+CSeSEym+g= +github.com/jaypipes/pcidb v1.0.0 h1:vtZIfkiCUE42oYbJS0TAq9XSfSmcsgo9IdxSm9qzYU8= +github.com/jaypipes/pcidb v1.0.0/go.mod h1:TnYUvqhPBzCKnH34KrIX22kAeEbDCSRJ9cqLRCuNDfk= +github.com/jessevdk/go-flags v1.4.0/go.mod h1:4FA24M0QyGHXBuZZK/XkWh8h0e1EYbRYJSGM75WSRxI= github.com/klauspost/compress v1.15.9 h1:wKRjX6JRtDdrE9qwa4b/Cip7ACOshUI4smpCQanqjSY= github.com/klauspost/compress v1.15.9/go.mod h1:PhcZ0MbTNciWF3rruxRgKxI5NkcHHrHUDtV4Yw2GlzU= +github.com/kr/pretty v0.1.0 h1:L/CwN0zerZDmRFUapSPitk6f+Q3+0za1rQkzVuMiMFI= +github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY= +github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE= github.com/mattn/go-colorable v0.1.12/go.mod h1:u5H1YNBxpqRaxsYJYSkiCWKzEfiAb1Gb520KVy5xxl4= github.com/mattn/go-colorable v0.1.13 h1:fFA4WZxdEF4tXPZVKMLwD8oUnCTTo08duU7wxecdEvA= github.com/mattn/go-colorable v0.1.13/go.mod h1:7S9/ev0klgBDR4GtXTXX8a3vIGJpMovkB8vQcUbaXHg= @@ -29,10 +45,13 @@ github.com/mattn/go-isatty v0.0.17 h1:BTarxUcIeDqL27Mc+vyvdWYSL28zpIhv3RoTdsLMPn github.com/mattn/go-isatty v0.0.17/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM= github.com/mattn/go-runewidth v0.0.14 h1:+xnbZSEeDbOIg5/mE6JF0w6n9duR1l3/WmbinWVwUuU= github.com/mattn/go-runewidth v0.0.14/go.mod h1:Jdepj2loyihRzMpdS35Xk/zdY8IAYHsh153qUoGf23w= +github.com/mitchellh/go-homedir v1.1.0 h1:lukF9ziXFxDFPkA1vsr5zpc1XuPDn/wFntq5mG+4E0Y= +github.com/mitchellh/go-homedir v1.1.0/go.mod h1:SfyaCUpYCn1Vlf4IUYiD9fPX4A5wJrkLzIz1N1q0pr0= github.com/onsi/ginkgo/v2 v2.9.2 h1:BA2GMJOtfGAfagzYtrAlufIP0lq6QERkFmHLMLPwFSU= github.com/onsi/gomega v1.27.6 h1:ENqfyGeS5AX/rlXDd/ETokDz93u0YufY1Pgxuy/PvWE= github.com/philhofer/fwd v1.1.1 h1:GdGcTjf5RNAxwS4QLsiMzJYj5KEvPJD3Abr261yRQXQ= github.com/philhofer/fwd v1.1.1/go.mod h1:gk3iGcWd9+svBvR0sR+KPcfE+RNWozjowpeBVG3ZVNU= +github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4= github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0= github.com/rivo/uniseg v0.2.0 h1:S1pD9weZBuJdFmowNwbpi7BJ8TNftyUImj/0WQi72jY= github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc= @@ -73,6 +92,7 @@ golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJ golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20190916202348-b4ddaad3f8a3/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= @@ -97,4 +117,11 @@ golang.org/x/tools v0.7.0 h1:W4OVu8VVOaIO0yzWMNdepAulS7YfoS3Zabrm8DOXXU4= golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= +gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= +gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127 h1:qIbj1fsPNlZgppZ+VLlY7N33q108Sa+fhmuc+sWQYwY= +gopkg.in/yaml.v1 v1.0.0-20140924161607-9f9df34309c0/go.mod h1:WDnlLJ4WF5VGsH/HVa3CI79GS0ol3YnhVnKP89i0kNg= +gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY= +gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ= gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= +howett.net/plist v1.0.0 h1:7CrbWYbPPO/PyNy38b2EB/+gYbjCe2DXBxgtOOZbSQM= +howett.net/plist v1.0.0/go.mod h1:lqaXoTrLY4hg8tnEzNru53gicrbv7rrk+2xJA/7hw9g= diff --git a/main.go b/main.go index 4c29c42..24861f2 100644 --- a/main.go +++ b/main.go @@ -2,13 +2,12 @@ package main import ( "os" - "runtime" api "github.com/go-skynet/LocalAI/api" model "github.com/go-skynet/LocalAI/pkg/model" + "github.com/jaypipes/ghw" "github.com/rs/zerolog" "github.com/rs/zerolog/log" - "github.com/urfave/cli/v2" ) @@ -21,6 +20,12 @@ func main() { os.Exit(1) } + threads := 4 + cpu, err := ghw.CPU() + if err == nil { + threads = int(cpu.TotalCores) + } + app := &cli.App{ Name: "LocalAI", Usage: "OpenAI compatible API for running LLaMA/GPT models locally on CPU with consumer grade hardware.", @@ -37,7 +42,7 @@ func main() { Name: "threads", DefaultText: "Number of threads used for parallel computation. Usage of the number of physical cores in the system is suggested.", EnvVars: []string{"THREADS"}, - Value: runtime.NumCPU(), + Value: threads, }, &cli.StringFlag{ Name: "models-path",