Michael Yang
|
74bd09652d
ml/backend/ggml: load tensors in 32KiB chunks
|
1 개월 전 |
Jesse Gross
|
0fbfcf3c9c
model: Pass input tensor instead of raw data to models
|
1 개월 전 |
Jesse Gross
|
0c220935bd
input: Rename Options to Batch
|
1 개월 전 |
Jesse Gross
|
282bfaaa95
ollamarunner: Use a separate context per multimodal input
|
1 개월 전 |
Michael Yang
|
3e102b7dad
Update model/model.go
|
1 개월 전 |
Michael Yang
|
5e2e0b46b1
fix: error if image requested without vision model
|
1 개월 전 |
Jesse Gross
|
a1cda80bcb
model: Update encoder cache to use multimodal input processing handler
|
1 개월 전 |
Jesse Gross
|
a7e63b82be
ollamarunner: Improve multimodal input handling
|
1 개월 전 |
Daniel Hiltgen
|
1fdb351c37
New engine: vision models and auto-fallback (#9113)
|
1 개월 전 |
Michael Yang
|
3e8b8a1933
ml: update Context.Forward interface
|
2 달 전 |
Jesse Gross
|
bd6a7d5e64
ollamarunner: Pass runner performance parameters to backends
|
2 달 전 |
Bruce MacDonald
|
d006e1e09b
model: document high-level model interface (#9122)
|
2 달 전 |
Jesse Gross
|
ed443a0393
Runner for Ollama engine
|
4 달 전 |
Jesse Gross
|
d650ad398f
model: Load tensors behind an interface
|
3 달 전 |
Jesse Gross
|
4d4463b2bd
backend: Support graph computation that does not return an output
|
2 달 전 |
Michael Yang
|
58245413f4
next ollama runner (#7913)
|
2 달 전 |