This website requires JavaScript.
Explore
Help
Sign In
ilker
/
llmgw
Watch
2
Star
0
Fork
1
Code
Issues
Pull Requests
Actions
Packages
Projects
Releases
95
Wiki
Activity
Files
8a5a04ed772bd9d8d1092e67d4f9d0fef8abcc47
llmgw
/
internal
/
mirror
T
History
Ilker Manap
and
Claude Opus 5.5
be54f1617b
CI / test (push)
Successful in 10m36s
Details
A mirror download cut off carries on from where it got to, and is tried again
...
Co-Authored-By: Claude Opus 5.5 (1M context) <
noreply@anthropic.com
>
2026-10-30 17:47:32 +01:00
..
add.go
A mirror download cut off carries on from where it got to, and is tried again
2026-10-30 17:47:32 +01:00
api_test.go
Keep the control plane's fetches off link-local addresses, and see through NAT64, 6to4 and proxies
2026-10-04 10:48:01 +02:00
api.go
Weights from Hugging Face pinned to a commit and checked against the sha256 it published
2026-10-30 07:33:15 +01:00
client_test.go
Let the control plane call the mirror instead of somebody SSHing to it
2026-09-27 10:16:54 +02:00
client.go
The control plane uses whichever mirror answers
2026-10-29 13:43:27 +01:00
firewall_test.go
The firewall setting reaches the mirror machine and the store's members
2026-10-09 08:53:17 +02:00
firewall.go
The firewall setting reaches the mirror machine and the store's members
2026-10-09 08:53:17 +02:00
import.go
TensorRT-LLM as an engine, and models from Ollama into the mirror
2026-10-05 00:02:01 +02:00
manager_test.go
Hide the mirror's bookkeeping, bound GGUF array nesting, and forget old serve jobs and downloads
2026-10-04 10:56:16 +02:00
manager.go
Weights from Hugging Face pinned to a commit and checked against the sha256 it published
2026-10-30 07:33:15 +01:00
mirror_test.go
Mirror a many-file model whole, with its checksums, for vLLM
2026-10-01 12:21:04 +02:00
mirror.go
Offline sites and Kubernetes: llmgw bundle create, import and trust, offline.mirror, server init --bundle; a Helm chart for the control plane
2026-10-05 00:13:39 +02:00
ollama_test.go
TensorRT-LLM as an engine, and models from Ollama into the mirror
2026-10-05 00:02:01 +02:00
ollama.go
TensorRT-LLM as an engine, and models from Ollama into the mirror
2026-10-05 00:02:01 +02:00
peer_test.go
Weights from Hugging Face pinned to a commit and checked against the sha256 it published
2026-10-30 07:33:15 +01:00
peer.go
A mirror with peers records the checksums of files that had none, so they are copied too
2026-10-29 18:36:59 +01:00
resume_test.go
A mirror download cut off carries on from where it got to, and is tried again
2026-10-30 17:47:32 +01:00
safefetch.go
Keep the control plane's fetches off link-local addresses, and see through NAT64, 6to4 and proxies
2026-10-04 10:48:01 +02:00
sources.go
The control plane uses whichever mirror answers
2026-10-29 13:43:27 +01:00
tombstone.go
A file removed outside the running mirror is no longer reported, and its removal reaches the peers
2026-10-29 19:25:00 +01:00
upload_test.go
Trained adapters published, private to their owners like the knowledge bases they come from
2026-10-08 21:30:50 +02:00