Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
readme: add Hexabot to the list of community integrations
4157d1f Med Marrouchi committed 2 years ago
Merge pull request #7456 from ollama/mxyng/llama3.2-vision-mem
f247a62 Michael Yang committed 2 years ago
CI: omit unused tools for faster release builds (#7432)
b8d5036 Daniel Hiltgen committed 2 years ago
runner.go: Only allocate 1 element embedding batches for mllama
a103dae Jesse Gross committed 2 years ago
runner.go: Don't set cross attention before sending embeddings
26acdcf Jesse Gross committed 2 years ago
Refine default thread selection for NUMA systems (#7322)
16f4eab Daniel Hiltgen committed 2 years ago
Remove submodule and shift to Go server - 0.4.0 (#7157)
b754f5a Daniel Hiltgen committed 2 years ago
windows: Support alt install paths, fit and finish (#6967)
91dfbb1 Daniel Hiltgen committed 2 years ago
add more tests for getting the optimal tiled canvas (#7411)
db1842b Patrick Devine committed 2 years ago
runner.go: Better handle return NULL values from llama.cpp
de1557a Jesse Gross committed 2 years ago
add mllama image processing to the generate handler (#7384)
084929c Patrick Devine committed 2 years ago