Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Commits on main

ci: switch mac builder to arm64 (#11379)
Daniel Hiltgen committed 1 year ago
191d942
readme: update the llama.cpp github link (#11427)
Haiyue Wang committed 1 year ago
e840ccb
compile bf16 support into ggml-metal (#11430)
Michael Yang committed 1 year ago
b4fe3ad
api: fix unreachable status err (#11423)
Bruce MacDonald committed 1 year ago
92c2e8a
docs: fix typo in macos.md (#11425)
Marcelo Fornet committed 1 year ago
2e3fd86
acef9b4
ggml: Disable unused pipeline parallelism
Jesse Gross committed 1 year ago
9a43994
Only load supported models on new engine (#11362)
Daniel Hiltgen committed 1 year ago
f8a6e88
ggml: Report ordinal IDs for AMD GPUs on Windows
Jesse Gross committed 1 year ago
35fda7b
doc: add MacOS docs (#11334)
Daniel Hiltgen committed 1 year ago
66fb857
Reduce default parallelism to 1 (#11330)
Daniel Hiltgen committed 1 year ago
20c3266
API/CLI context enhancements (#11331)
Daniel Hiltgen committed 1 year ago
34088db
add `tool_name` to api.md (#11326)
Parth Sareen committed 1 year ago
43107b1
template: add tool result compatibility (#11294)
Parth Sareen committed 1 year ago
1f91cb0
ci: modularization (#11324)
Daniel Hiltgen committed 1 year ago
12d8ad0
592d21e
readme: update Ollama icon size
Jeffrey Morgan committed 1 year ago
5a08b01
int: add performance integration tests (#11173)
Daniel Hiltgen committed 1 year ago
4f473e2
doc: add NVIDIA blackwell to supported list (#11307)
Daniel Hiltgen committed 1 year ago
9d60bb4
Update base image to Ubuntu 24.04 LTS (#9681)
Vincent RAMPAL committed 1 year ago
f371260
doc: Update link for mac install (#11288)
Daniel Hiltgen committed 1 year ago
c9e6d77
mimic logs for layers on new engine (#11278)
Daniel Hiltgen committed 1 year ago
2c4ce40
chore: cleanup comments + unused vars (#11225)
Michael Yang committed 1 year ago
4129af9