Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Commits on main

comments
Michael Yang committed 2 years ago
2c3fe1f
update message processing
Michael Yang committed 2 years ago
269ed6e
fix typo in cgo directives in `llm.go` (#5501)
Jeffrey Morgan committed 2 years ago
78fb33d
update llama.cpp submodule to `d7fd29f` (#5475)
Jeffrey Morgan committed 2 years ago
8f8e736
af28b94
Fix assert on small embedding inputs (#5491)
Jeffrey Morgan committed 2 years ago
e9188e9
Merge pull request #4412 from dhiltgen/win_docs
Daniel Hiltgen committed 2 years ago
78eddfc
Merge pull request #5466 from dhiltgen/fix_clip_unicode
Daniel Hiltgen committed 2 years ago
02c24d3
Document older win10 terminal problems
Daniel Hiltgen committed 2 years ago
52abc8a
fix: use `envconfig.ModelsDir` directly (#4821)
Anatoli Babenia committed 2 years ago
0d16eb3
Merge pull request #5447 from dhiltgen/fix_keepalive
Daniel Hiltgen committed 2 years ago
8072e20
Only set default keep_alive on initial model load
Daniel Hiltgen committed 2 years ago
955f2a4
Prevent loading models larger than total memory
Daniel Hiltgen committed 2 years ago
3c75113
ccd7785
daed063
0d4dd70
Fix corner cases on tmp cleaner on mac
Daniel Hiltgen committed 2 years ago
0e982bc
Fix clip model loading with unicode paths
Daniel Hiltgen committed 2 years ago
6298f49
Better nvidia GPU discovery logging
Daniel Hiltgen committed 2 years ago
ef757da
e535229
fix generate template
Michael Yang committed 2 years ago
65a5040
OpenAI: v1/completions compatibility (#5209)
royjhan committed 2 years ago
d626b99
dddb58a
400056e
Merge pull request #5442 from dhiltgen/concurrency_docs
Daniel Hiltgen committed 2 years ago
d2f1902
Add windows radeon concurreny note
Daniel Hiltgen committed 2 years ago
69c04ee