 Jeffrey Morgan
|
e093db92c4
sample: temporarily use grammars for constrained generation in new engine (#9586)
|
il y a 1 mois |
 Michael Yang
|
05a01fdecb
ml/backend/ggml: consolidate system info logging
|
il y a 2 mois |
|
Michael Yang
|
657685e85d
fix: replace deprecated functions
|
il y a 2 mois |
|
Michael Yang
|
a59f665235
ml/backend/ggml: fix debug logging
|
il y a 2 mois |
|
Jeffrey Morgan
|
d7d7e99662
llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)
|
il y a 2 mois |
 Diego Pereira
|
928911bc68
runner: avoid buffer overwrite when generating multiple embeddings (#8714)
|
il y a 2 mois |
|
Michael Yang
|
548a9f56a6
Revert "cgo: use O3"
|
il y a 3 mois |
|
Michael Yang
|
bea1f1fac6
cgo: use O3
|
il y a 3 mois |
|
Michael Yang
|
dcfb7a105c
next build (#8539)
|
il y a 3 mois |
|
Jeffrey Morgan
|
1deafd8254
llama: update vendored code to commit 46e3556 (#8308)
|
il y a 3 mois |
 Daniel Hiltgen
|
60f75560a2
runner: switch logging back to stderr (#8091)
|
il y a 4 mois |
 Blake Mizerany
|
9039c821a2
llama: preserve field order in user-defined JSON schemas (#8002)
|
il y a 4 mois |
|
Jeffrey Morgan
|
527cc97899
llama: update vendored code to commit 40c6d79f (#7875)
|
il y a 4 mois |
|
Daniel Hiltgen
|
b9ccb3741e
Remove unused runner CpuFeatures (#8032)
|
il y a 4 mois |
|
Daniel Hiltgen
|
4879a234c4
build: Make target improvements (#7499)
|
il y a 4 mois |
 Parth Sareen
|
630e7dc6ff
api: structured outputs - chat endpoint (#7900)
|
il y a 5 mois |
 Sam
|
1bdab9fdb1
llm: introduce k/v context quantization (vRAM improvements) (#6279)
|
il y a 5 mois |
 Jesse Gross
|
7121dfa309
runner.go: Retry decoding after defragmentation if needed
|
il y a 5 mois |
 Gabe Goodhart
|
807ace5b1f
fix(runner): Set logits to 0 if false on Batch.Add
|
il y a 5 mois |
|
Michael Yang
|
549c2bdfcf
Merge pull request #7657 from ollama/mxyng/sync
|
il y a 5 mois |
|
Michael Yang
|
5b3393b6a2
fix(mllama): sync backend between batches
|
il y a 5 mois |
|
Daniel Hiltgen
|
df011054fa
Jetpack support for Go server (#7217)
|
il y a 5 mois |
|
Jesse Gross
|
312d9de1d1
llama: Improve error handling
|
il y a 6 mois |
|
Jesse Gross
|
a103dae01e
runner.go: Only allocate 1 element embedding batches for mllama
|
il y a 6 mois |
|
Jesse Gross
|
c826e57475
runner.go: Better abstract vision model integration
|
il y a 6 mois |
|
Daniel Hiltgen
|
712e99d477
Soften windows clang requirement (#7428)
|
il y a 6 mois |
|
Daniel Hiltgen
|
b754f5a6a3
Remove submodule and shift to Go server - 0.4.0 (#7157)
|
il y a 6 mois |
|
Jesse Gross
|
de1557a0dc
runner.go: Better handle return NULL values from llama.cpp
|
il y a 6 mois |
|
Daniel Hiltgen
|
3085c47bea
Improve dependency gathering logic (#7345)
|
il y a 6 mois |
 Patrick Devine
|
c7cb0f0602
image processing for llama3.2 (#6963)
|
il y a 6 mois |
