andreas/llama-swap
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
1a8492650508d97ff6f179b55aa0b123790913e4
llama-swap/proxy
History
Benson Wong 1a84926505 proxy: add unload of single model (#318) 
This adds a new API endpoint, /api/models/unload/*model, that unloads a single model. In the UI when a model is in a ReadyState it will have a new button to unload it. 

Fixes #312
2025-09-24 20:53:48 -07:00
..
.gitignore
New UI (#157, #164)
2025-06-16 16:45:19 -07:00
config_posix_test.go
Add barebones but working implementation of model preload (#209, #235)
2025-08-14 10:27:28 -07:00
config_test.go
Add ${MODEL_ID} macro (#226)
2025-09-01 21:21:37 -07:00
config_windows_test.go
Add metrics logging for chat completion requests (#195)
2025-07-21 22:19:55 -07:00
config.go
Add ${MODEL_ID} macro (#226)
2025-09-01 21:21:37 -07:00
discardWriter.go
Add barebones but working implementation of model preload (#209, #235)
2025-08-14 10:27:28 -07:00
events.go
Add barebones but working implementation of model preload (#209, #235)
2025-08-14 10:27:28 -07:00
helpers_test.go
Add barebones but working implementation of model preload (#209, #235)
2025-08-14 10:27:28 -07:00
logMonitor_test.go
Add Event Bus (#184)
2025-07-01 22:17:35 -07:00
logMonitor.go
Fix High CPU (#189)
2025-07-15 18:04:30 -07:00
metrics_middleware.go
Support llama.cpp's cache_n in timings info (#287)
2025-09-06 13:58:02 -07:00
metrics_monitor.go
Support llama.cpp's cache_n in timings info (#287)
2025-09-06 13:58:02 -07:00
process_test.go
Strip comments before macro expansion in config (#193)
2025-07-15 10:14:16 -07:00
process.go
Fix nginx proxy buffering for streaming endpoints (#295)
2025-09-09 16:07:46 -07:00
processgroup_test.go
Fix #277 race condition in ProcessGroup.ProxyRequest when swap=true
2025-08-28 21:38:40 -07:00
processgroup.go
proxy: add unload of single model (#318)
2025-09-24 20:53:48 -07:00
proxymanager_api.go
proxy: add unload of single model (#318)
2025-09-24 20:53:48 -07:00
proxymanager_loghandlers.go
Fix nginx proxy buffering for streaming endpoints (#295)
2025-09-09 16:07:46 -07:00
proxymanager_test.go
proxy: add unload of single model (#318)
2025-09-24 20:53:48 -07:00
proxymanager.go
proxy: add unload of single model (#318)
2025-09-24 20:53:48 -07:00
sanitize_cors_test.go
Sanitize CORS headers (#85)
2025-04-01 08:43:53 -07:00
sanitize_cors.go
Sanitize CORS headers (#85)
2025-04-01 08:43:53 -07:00
ui_embed.go
New UI (#157, #164)
2025-06-16 16:45:19 -07:00