ggml-org/llama.cpp

common: download from URL, improve parallel download progress status

已關閉

#6,537 建立於 2024年4月8日

 (7 則留言) (0 個反應) (1 位負責人)C++ (21,786 個分叉)batch import
enhancementgood first issuehelp wantedsplit

倉庫指標

星標
 (124,222 顆星)
PR 合併指標
 (平均合併 6天 8小時) (30 天內合併 389 個 PR)

描述

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"

貢獻者指南