Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
server/internal: replace model delete API with new registry handler. (#9347)
2412adf Blake Mizerany committed 1 year ago
.github/workflows: swap order of go test and golangci-lint (#9389)
76e903c Blake Mizerany committed 1 year ago
ml/backend/ggml: follow on fixes after updating vendored code (#9388)
a527213 Jeffrey Morgan committed 1 year ago
llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)
d7d7e99 Jeffrey Morgan committed 1 year ago
.github: always run tests, and other helpful fixes (#9348)
0d69479 Blake Mizerany committed 1 year ago
Update ROCm (6.3 linux, 6.2 windows) and CUDA v12.8 (#9304)
e91ae3d Daniel Hiltgen committed 1 year ago
build: support Compute Capability 5.0, 5.2 and 5.3 for CUDA 12.x (#8567)
a499390 Pavol Rusnak committed 1 year ago
server/internal: copy bmizerany/ollama-go to internal package (#9294)
348b3e0 Blake Mizerany committed 1 year ago
config: allow setting context length through env var (#8938)
314573b Parth Sareen committed 1 year ago
ml/backend/ggml: fix crash on windows paths with wide characters (#9305)
8c13cfa Jeffrey Morgan committed 1 year ago