 Jesse Gross
|
f66216e399
ggml: Support heterogeneous KV cache layer sizes in memory estimation
|
vor 1 Monat |
 Bruce MacDonald
|
3892c3a703
llm: remove internal subprocess req and resp types (#9324)
|
vor 1 Monat |
 Daniel Hiltgen
|
ab39e08eb9
llm: auto detect models that require Ollama Engine (#1)
|
vor 1 Monat |
 Jeffrey Morgan
|
e093db92c4
sample: temporarily use grammars for constrained generation in new engine (#9586)
|
vor 1 Monat |
|
Jesse Gross
|
b70fc4d51e
model: Don't unconditionally add special tokens
|
vor 1 Monat |
|
Daniel Hiltgen
|
1fdb351c37
New engine: vision models and auto-fallback (#9113)
|
vor 1 Monat |
|
Jeffrey Morgan
|
5296f487a8
llm: attempt to evaluate symlinks, but do not fail (#9089)
|
vor 2 Monaten |
|
Jeffrey Morgan
|
f05774b04c
llm: do not evaluate symlink for exe path lookup (#9088)
|
vor 2 Monaten |
|
Jesse Gross
|
ed443a0393
Runner for Ollama engine
|
vor 4 Monaten |
 Michael Yang
|
58245413f4
next ollama runner (#7913)
|
vor 2 Monaten |
|
Jeffrey Morgan
|
4759ecae19
ml/backend/ggml: fix library loading on macOS amd64 (#8827)
|
vor 2 Monaten |
|
Jeffrey Morgan
|
50566113ac
llm: do not error if LibOllamaPath does not exist (#8801)
|
vor 2 Monaten |
|
Michael Yang
|
dcfb7a105c
next build (#8539)
|
vor 3 Monaten |
|
Jeffrey Morgan
|
1deafd8254
llama: update vendored code to commit 46e3556 (#8308)
|
vor 3 Monaten |
 Blake Mizerany
|
2ddc32d5c5
llm: do not error on "null" format (#8139)
|
vor 4 Monaten |
|
Blake Mizerany
|
87f0a49fe6
llm: do not silently fail for supplied, but invalid formats (#8130)
|
vor 4 Monaten |
|
Jeffrey Morgan
|
0f06a6daa7
llm: loosen format check to default to no format (#8127)
|
vor 4 Monaten |
|
Blake Mizerany
|
9039c821a2
llama: preserve field order in user-defined JSON schemas (#8002)
|
vor 4 Monaten |
|
Jeffrey Morgan
|
527cc97899
llama: update vendored code to commit 40c6d79f (#7875)
|
vor 4 Monaten |
|
Daniel Hiltgen
|
4879a234c4
build: Make target improvements (#7499)
|
vor 4 Monaten |
 Parth Sareen
|
de52b6c2f9
bugfix: "null" value json mode (#7979)
|
vor 4 Monaten |
|
Parth Sareen
|
630e7dc6ff
api: structured outputs - chat endpoint (#7900)
|
vor 4 Monaten |
 Sam
|
539be43640
llm: normalise kvct parameter handling (#7926)
|
vor 5 Monaten |
|
Sam
|
1bdab9fdb1
llm: introduce k/v context quantization (vRAM improvements) (#6279)
|
vor 5 Monaten |
 ItzCrazyKns
|
e3936d4fb3
Support Multiple LoRa Adapters (#7667)
|
vor 5 Monaten |
|
Daniel Hiltgen
|
b85520bfb9
logs: explain client aborts better (#7783)
|
vor 5 Monaten |
|
Daniel Hiltgen
|
909a88c5c0
Improve crash reporting (#7728)
|
vor 5 Monaten |
|
Daniel Hiltgen
|
81d55d3e4d
fix index out of range on zero layer metal load (#7696)
|
vor 5 Monaten |
|
Daniel Hiltgen
|
df011054fa
Jetpack support for Go server (#7217)
|
vor 5 Monaten |
|
Jesse Gross
|
a909417602
runner.go: Remove unused arguments
|
vor 6 Monaten |
