Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
fs/ggml: add missing architecture to OllamaEngineRequired() (#11206)
3944602 Jeffrey Morgan committed 1 year ago
Merge pull request #10238 from ollama/drifkin/array-head-count-simple
cc6463e Devon Rifkin committed 1 year ago
Reapply "feat: incremental gguf parser (#10822)" (#11114) (#11119)
0a066cf Michael Yang committed 1 year ago
Revert "Revert "ggml: Export GPU UUIDs" (#11115)" (#11117)
6baf1e3 Jeffrey Morgan committed 1 year ago
Revert "feat: incremental gguf parser (#10822)" (#11114)
a6e64fb Jeffrey Morgan committed 1 year ago
tools: return empty arguments object instead of null (#11113)
55bbf3b Jeffrey Morgan committed 1 year ago
tools: fix parsing tool calls without any parameters (#11101)
6bda1d2 Jeffrey Morgan committed 1 year ago