]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 703f9e3)
Add resumable downloads for llama-server model loading (#15963)
authorEric Curtin <redacted>
Thu, 18 Sep 2025 15:22:50 +0000 (16:22 +0100)
committerGitHub <redacted>
Thu, 18 Sep 2025 15:22:50 +0000 (16:22 +0100)
commit4ca088b036313c2d8e682f4cfeb7c29edd85d0b9
treefd4d34d0abb632098e1a7f9035cbf0596000d5c1tree
parent703f9e32c4eb3166f8d63007c26e31a1466c21afcommit | diff
Add resumable downloads for llama-server model loading (#15963)

- Implement resumable downloads in common_download_file_single function
- Add detection of partial download files (.downloadInProgress)
- Check server support for HTTP Range requests via Accept-Ranges header
- Implement HTTP Range request with "bytes=<start>-" header
- Open files in append mode when resuming vs create mode for new downloads

Signed-off-by: Eric Curtin <redacted>
common/arg.cpp diff | blob | history
Packaging of ggml-org/llama.cpp