feat(llama.cpp): estimate vram usage (#5299)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-05-02 17:40:26 +02:00 committed by GitHub
parent bace6516f1
commit 5c6cd50ed6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 131 additions and 21 deletions

6
go.mod
View file

@ -27,6 +27,7 @@ require (
github.com/golang/protobuf v1.5.4
github.com/google/go-containerregistry v0.19.2
github.com/google/uuid v1.6.0
github.com/gpustack/gguf-parser-go v0.17.0
github.com/grpc-ecosystem/grpc-gateway v1.5.0
github.com/hpcloud/tail v1.0.0
github.com/ipfs/go-log v1.0.5
@ -110,6 +111,7 @@ require (
github.com/pion/turn/v2 v2.1.6 // indirect
github.com/pion/turn/v4 v4.0.0 // indirect
github.com/pion/webrtc/v4 v4.0.9 // indirect
github.com/rs/dnscache v0.0.0-20230804202142-fc85eb664529 // indirect
github.com/savsgio/gotils v0.0.0-20230208104028-c358bd845dee // indirect
github.com/shirou/gopsutil/v4 v4.24.7 // indirect
github.com/wlynxg/anet v0.0.5 // indirect
@ -188,7 +190,7 @@ require (
github.com/hashicorp/go-multierror v1.1.1 // indirect
github.com/hashicorp/golang-lru v1.0.2 // indirect
github.com/hashicorp/golang-lru/v2 v2.0.7 // indirect
github.com/henvic/httpretty v0.1.3 // indirect
github.com/henvic/httpretty v0.1.4 // indirect
github.com/huandu/xstrings v1.5.0 // indirect
github.com/huin/goupnp v1.3.0 // indirect
github.com/ipfs/boxo v0.27.4 // indirect
@ -278,7 +280,7 @@ require (
github.com/shoenig/go-m1cpu v0.1.6 // indirect
github.com/shopspring/decimal v1.4.0 // indirect
github.com/sirupsen/logrus v1.9.3 // indirect
github.com/smallnest/ringbuffer v0.0.0-20240423223918-bab516b2000b // indirect
github.com/smallnest/ringbuffer v0.0.0-20241116012123-461381446e3d // indirect
github.com/songgao/packets v0.0.0-20160404182456-549a10cd4091 // indirect
github.com/spaolacci/murmur3 v1.1.0 // indirect
github.com/spf13/cast v1.7.0 // indirect