ggml-org/llama.cpp

common: download from URL, improve parallel download progress status

Chiusa

#6537 aperta il 8 apr 2024

 (7 commenti) (0 reazioni) (1 assegnatario)C++ (21.764 fork)batch import
enhancementgood first issuehelp wantedsplit

Metriche repository

Star
 (124.134 stelle)
Metriche merge PR
 (Merge medio 6g 8h) (389 PR mergiate in 30 g)

Descrizione

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"

Guida contributor