 Blake Mizerany
|
2099e2d267
CONTRIBUTING: provide clarity on good commit messages, and bad (#9405)
|
2 months ago |
 Bruce MacDonald
|
0c1041ad85
runner: default to greedy sampler for performance (#9407)
|
2 months ago |
 Parth Sareen
|
c245b0406f
sample: remove transforms from greedy sampling (#9377)
|
2 months ago |
 Michael Yang
|
8b194b7520
kvcache: update tests
|
2 months ago |
|
Michael Yang
|
3e8b8a1933
ml: update Context.Forward interface
|
2 months ago |
|
Blake Mizerany
|
41dc280491
server/internal/registry: implement CloseNotify and Flush (for now) (#9402)
|
2 months ago |
|
Michael Yang
|
53d2990d9b
model: add bos token if configured
|
2 months ago |
 Jesse Gross
|
e185c08ad9
go.mod: Use full version for go 1.24.0
|
2 months ago |
|
Blake Mizerany
|
2412adf42b
server/internal: replace model delete API with new registry handler. (#9347)
|
2 months ago |
 Steven Hartland
|
be2ac1ed93
docs: fix api examples link (#9360)
|
2 months ago |
 Eries Trisnadi
|
dc13813a03
server: allow vscode-file origins (#9313)
|
2 months ago |
|
Michael Yang
|
d6af13efed
runner: simplify tensor split parsing
|
2 months ago |
|
Michael Yang
|
a59f665235
ml/backend/ggml: fix debug logging
|
2 months ago |
 Daniel Hiltgen
|
688925aca9
Windows ARM build (#9120)
|
2 months ago |
|
Blake Mizerany
|
76e903cf9d
.github/workflows: swap order of go test and golangci-lint (#9389)
|
2 months ago |
 Jeffrey Morgan
|
a5272130c4
ml/backend/ggml: follow on fixes after updating vendored code (#9388)
|
2 months ago |
|
Jeffrey Morgan
|
d7d7e99662
llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)
|
2 months ago |
 Gordon Kamer
|
2db96c18e7
readme: add Nichey to community integrations (#9370)
|
2 months ago |
|
Daniel Hiltgen
|
e12af460ed
Add cuda Blackwell architecture for v12 (#9350)
|
2 months ago |
|
Jeffrey Morgan
|
3ad4bc8afe
llama: removed unused 'vendoring' file (#9351)
|
2 months ago |
|
Blake Mizerany
|
0d694793f2
.github: always run tests, and other helpful fixes (#9348)
|
2 months ago |
|
Daniel Hiltgen
|
e91ae3d47d
Update ROCm (6.3 linux, 6.2 windows) and CUDA v12.8 (#9304)
|
2 months ago |
 José Pekkarinen
|
6ecd7f64ba
docker: upgrade rocm to 6.3.3 (#8211)
|
2 months ago |
 Chuanhui Liu
|
888855675e
docs: rocm install link (#9346)
|
2 months ago |
|
Michael Yang
|
b16367b4b2
fix: add back bf16 support
|
2 months ago |
 Pavol Rusnak
|
a499390648
build: support Compute Capability 5.0, 5.2 and 5.3 for CUDA 12.x (#8567)
|
2 months ago |
 frob
|
4df98f3eb5
Move cgroups fix out of AMD section. (#9072)
|
2 months ago |
|
Blake Mizerany
|
348b3e0983
server/internal: copy bmizerany/ollama-go to internal package (#9294)
|
2 months ago |
|
Parth Sareen
|
0b7e1676eb
sample: add sampling package for new engine (#8410)
|
2 months ago |
|
Parth Sareen
|
314573bfe8
config: allow setting context length through env var (#8938)
|
2 months ago |
