 Patrick Devine
|
ef378ad673
gemma3 quantization (#9776)
|
hai 1 mes |
 Daniel Hiltgen
|
2d2247e59e
Align versions for local builds (#9635)
|
hai 1 mes |
 Jesse Gross
|
7bf793a600
gemma3: Allow multiple image in a single input
|
hai 1 mes |
|
Jesse Gross
|
282bfaaa95
ollamarunner: Use a separate context per multimodal input
|
hai 1 mes |
|
Jesse Gross
|
9679f40146
ml: Allow models to constrain inputs to a single batch
|
hai 1 mes |
 Bruce MacDonald
|
3892c3a703
llm: remove internal subprocess req and resp types (#9324)
|
hai 1 mes |
 Blake Mizerany
|
4e320b8b90
server/internal/chunks: remove chunks package (#9755)
|
hai 1 mes |
|
Blake Mizerany
|
eb2b22b042
server/internal/client: use chunksums for concurrent blob verification (#9746)
|
hai 1 mes |
 Michael Yang
|
4ea4d2b189
Merge pull request #9703 from ollama/mxyng/gemma3-memory
|
hai 1 mes |
|
Michael Yang
|
8d76fa23ef
count non-repeating vision layers
|
hai 1 mes |
 Bradley Erickson
|
74b44fdf8f
docs: Add OLLAMA_ORIGINS for browser extension support (#9643)
|
hai 1 mes |
|
Michael Yang
|
65b88c544f
fix divide by zero
|
hai 1 mes |
|
Michael Yang
|
a422ba39c9
roughly count gemma3 graph
|
hai 1 mes |
|
Michael Yang
|
d2ec22371e
count all vision tensors
|
hai 1 mes |
|
Michael Yang
|
033cec232a
count gemma3 vision tensors
|
hai 1 mes |
|
Michael Yang
|
543240fb5f
Merge pull request #9741 from ollama/mxyng/visionless
|
hai 1 mes |
|
Patrick Devine
|
4bed739259
add verbose mode to the show command (#9640)
|
hai 1 mes |
|
Patrick Devine
|
80c7ce381b
fix: change default context size for gemma3 (#9744)
|
hai 1 mes |
|
Michael Yang
|
ccfd41c4f0
Merge pull request #9742 from ollama/mxyng/engine-error-embeddings
|
hai 1 mes |
|
Michael Yang
|
3e102b7dad
Update model/model.go
|
hai 1 mes |
|
Michael Yang
|
ec46f3286c
engine: error on embeddings; not currently implemented
|
hai 1 mes |
|
Michael Yang
|
5e2e0b46b1
fix: error if image requested without vision model
|
hai 1 mes |
|
Michael Yang
|
45a13b1dec
Merge pull request #9688 from Shane-XB-Qian/debug_mistype_lld
|
hai 1 mes |
 Parth Sareen
|
5c0b663969
sample: separate softmax and temperature transforms (#9732)
|
hai 1 mes |
 shane.xb.qian
|
30d7a59ba8
ollama-debug.c: change 'ld' to 'PRIi64'
|
hai 1 mes |
|
ParthSareen
|
4aeb67ef4c
sample: do all sorting in topK
|
hai 1 mes |
|
ParthSareen
|
3ba91634c1
sample: simplify top_k=0 sorting
|
hai 1 mes |
|
ParthSareen
|
1b7433b71e
sample: use container/heap for top_k
|
hai 1 mes |
|
Bruce MacDonald
|
a70820daa0
models/gemma3: remove final logit softcap (#9692)
|
hai 1 mes |
 Shane-XB-Qian
|
6b45b1d6b4
cli: adding support ctrl-n/p like general cli (#9136)
|
hai 1 mes |
