dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 02:24:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

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

Browse source 
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
Download patch file Download diff file Expand all files Collapse all files

4
core/cli/util.go
View file

@ -7,11 +7,11 @@ import (
"github.com/rs/zerolog/log"
gguf "github.com/gpustack/gguf-parser-go"
cliContext "github.com/mudler/LocalAI/core/cli/context"
"github.com/mudler/LocalAI/core/config"
"github.com/mudler/LocalAI/core/gallery"
"github.com/mudler/LocalAI/pkg/downloader"
gguf "github.com/thxcode/gguf-parser-go"
)
type UtilCMD struct {
@ -51,7 +51,7 @@ func (u *GGUFInfoCMD) Run(ctx *cliContext.Context) error {
log.Info().
Any("eosTokenID", f.Tokenizer().EOSTokenID).
Any("bosTokenID", f.Tokenizer().BOSTokenID).
Any("modelName", f.Model().Name).
Any("modelName", f.Metadata().Name).
Any("architecture", f.Architecture().Architecture).Msgf("GGUF file loaded: %s", u.Args[0])
log.Info().Any("tokenizer", fmt.Sprintf("%+v", f.Tokenizer())).Msg("Tokenizer")