ggml-org/llama.cpp

common: download from URL, improve parallel download progress status

クローズ

#6,537 opened on 2024/04/08

 (7 件のコメント) (0 件のリアクション) (1 人の担当者)C++ (21,786 件のフォーク)batch import
enhancementgood first issuehelp wantedsplit

Repository metrics

Stars
 (124,222 個のスター)
PR merge metrics
 (平均マージ 6d 8h) (30d で 389 merged PRs)

説明

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"

コントリビューターガイド