ggml-org/llama.cpp

common: download from URL, improve parallel download progress status

Fermée

#6 537 ouverte le 8 avr. 2024

 (7 commentaires) (0 réaction) (1 personne assignée)C++ (21 825 forks)batch import
enhancementgood first issuehelp wantedsplit

Métriques du dépôt

Stars
 (124 401 étoiles)
Métriques de merge PR
 (Merge moyen 6j 8h) (389 PRs mergées en 30 j)

Description

Context

When downloading a sharded model, files are downloaded in parallel, it was added in:

  • #6192

The progressions of each download conflict: image

Need to properly implement CURLOPT_NOPROGRESS for parallel download.

Example in #6515:

main --hf-repo ggml-org/models \
  --hf-file grok-1/grok-1-q4_0-00001-of-00009.gguf \
  --model   models/grok-1-q4_0-00001-of-00009.gguf \
  -ngl 64
   --prompt "I believe the meaning of life is"

Guide contributeur