 Matt Williams
|
1eefebe392
add faq for what is context
|
1 year ago |
|
Matt Williams
|
5a85070c22
Update readmes, requirements, packagejsons, etc for all examples (#1452)
|
1 year ago |
|
Matt Williams
|
291700c92d
Clean up documentation (#1506)
|
1 year ago |
 Daniel Hiltgen
|
9db28af84e
Merge pull request #1675 from dhiltgen/less_verbose
|
1 year ago |
 Daniel Hiltgen
|
e5202eb687
Quiet down llama.cpp logging by default
|
1 year ago |
|
Daniel Hiltgen
|
96fb441abd
Merge pull request #1146 from dhiltgen/ext_server_cgo
|
1 year ago |
|
Daniel Hiltgen
|
495c06e4a6
Fix doc glitch
|
1 year ago |
|
Daniel Hiltgen
|
fa24e73b82
Remove CPU build, fixup linux build script
|
1 year ago |
|
Daniel Hiltgen
|
325d74985b
Fix CPU performance on hyperthreaded systems
|
1 year ago |
 Bruce MacDonald
|
fabf2f3467
allow for starting llava queries with filepath (#1549)
|
1 year ago |
|
Daniel Hiltgen
|
d9cd3d9667
Revive windows build
|
1 year ago |
 Patrick Devine
|
a607d922f0
add FAQ for slow networking in WSL2 (#1646)
|
1 year ago |
|
Daniel Hiltgen
|
7555ea44f8
Revamp the dynamic library shim
|
1 year ago |
 Jeffrey Morgan
|
df06812494
Update api.md
|
1 year ago |
|
Daniel Hiltgen
|
1d1eb1688c
Additional nvidial-ml path to check
|
1 year ago |
 Michael Yang
|
23dc179350
Merge pull request #1619 from jmorganca/mxyng/fix-version-test
|
1 year ago |
|
Michael Yang
|
63aac0edc5
fix(test): use real version string for comparison
|
1 year ago |
|
Daniel Hiltgen
|
6558f94ed0
Fix darwin intel build
|
1 year ago |
 Erick Ghaumez
|
1ca484f67e
Add Langchain Dart library (#1564)
|
1 year ago |
|
Jeffrey Morgan
|
72b0c32fe9
Update README.md
|
1 year ago |
|
Jeffrey Morgan
|
68c28224f8
Update README.md
|
1 year ago |
|
Daniel Hiltgen
|
54dbfa4c4a
Carry ggml-metal.metal as payload
|
1 year ago |
|
Daniel Hiltgen
|
5646826a79
Add WSL2 path to nvidia-ml.so library
|
1 year ago |
|
Daniel Hiltgen
|
3269535a4c
Refine handling of shim presence
|
1 year ago |
|
Daniel Hiltgen
|
1b991d0ba9
Refine build to support CPU only
|
1 year ago |
|
Daniel Hiltgen
|
51082535e1
Add automated test for multimodal
|
1 year ago |
|
Daniel Hiltgen
|
9adca7f711
Bump llama.cpp to b1662 and set n_parallel=1
|
1 year ago |
|
Daniel Hiltgen
|
89bbaafa64
Build linux using ubuntu 20.04
|
1 year ago |
|
Daniel Hiltgen
|
35934b2e05
Adapted rocm support to cgo based llama.cpp
|
1 year ago |
 65a
|
f8ef4439e9
Use build tags to generate accelerated binaries for CUDA and ROCm on Linux.
|
1 year ago |
