 AlpinDale
|
0247bdcd27
inline model switching
|
3 weeks ago |
|
AlpinDale
|
3391557b64
take yaml config in model load endpoint
|
3 weeks ago |
|
AlpinDale
|
118bbfec5a
take more args in model load field
|
3 weeks ago |
|
AlpinDale
|
8a4fc7f761
add a simple model load endpoint
|
3 weeks ago |
|
AlpinDale
|
b94c8840b5
fix model unload endpoint
|
3 weeks ago |
|
AlpinDale
|
b47a39026d
feat: introduce MQAphroditeEngine
|
4 weeks ago |
 AlpinDale
|
638c08d9dc
fix: clean shutdown issues (#1047)
|
1 month ago |
|
AlpinDale
|
313e198557
api: implement OpenAI-compatible tools API for Hermes/Mistral models (#993)
|
1 month ago |
|
AlpinDale
|
231693151b
benchmarks: add `--async-engine` arg to throughput benchmark (#988)
|
1 month ago |
|
AlpinDale
|
a3c03db735
fix: inline model loading conflicts with lora (#930)
|
1 month ago |
|
AlpinDale
|
59d1d59028
api: support aphrodite_config.yaml with inline loading (#929)
|
1 month ago |
|
AlpinDale
|
d46e70ac98
api: add inline model loading (#928)
|
1 month ago |
|
AlpinDale
|
53d0ba7c7c
api: add endpoint for loading and unloading the model (#926)
|
1 month ago |
|
AlpinDale
|
6fbab320e7
api: error suppression cleanup + timeout suppression on aborts (#905)
|
1 month ago |
|
AlpinDale
|
a00ab49e21
api: add client timeouts for the ZeroMQ server (#897)
|
1 month ago |
|
AlpinDale
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
1 month ago |
|
AlpinDale
|
901900854e
chore: consolidate environment variables within one file (#882)
|
1 month ago |
|
AlpinDale
|
ce6e3d63f7
api: better startup failure UX (#881)
|
1 month ago |
|
AlpinDale
|
b5aa11020b
api: fix crashes under very high loads (#878)
|
1 month ago |
|
AlpinDale
|
2fa112f86b
feat: update to serviceinfo v0.2 (#808)
|
2 months ago |
|
AlpinDale
|
72fbfa1b5b
feat: add serviceinfo endpoint (#807)
|
2 months ago |
|
AlpinDale
|
6145deab4a
frontend: enable kobold api by default (#803)
|
2 months ago |
|
AlpinDale
|
43965f7bd9
fix: kobold lite embedded UI on windows (#797)
|
2 months ago |
|
AlpinDale
|
0256ed236b
feat: windows support (#790)
|
2 months ago |
|
AlpinDale
|
a604ab69c4
fix: kobold api for horde (#763)
|
3 months ago |
|
AlpinDale
|
ad181e3fef
feat: bring back dynatemp (#754)
|
4 months ago |
|
AlpinDale
|
9d9722b1c1
fix: metrics endpoint with RPC server (#747)
|
4 months ago |
|
AlpinDale
|
2d044af0e1
chore: spawn engine process from api server process (#703)
|
4 months ago |
|
AlpinDale
|
1d3a1fec47
feat: add load/unload endpoints for soft-prompts (#694)
|
4 months ago |
|
AlpinDale
|
c34a6ac8e4
feat: add lora loading/unloading api endpoint (#693)
|
4 months ago |
