Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
preserve tool definition and call JSON ordering (#13525)
e51dead Devon Rifkin committed 10 months ago
docs/capabilities/vision: fix curl related code snippet (#13615)
d087e46 Harry V. Kiselev committed 10 months ago
server: return error when embedding contains NaN or Inf values (#13599)
37f6f3a lif committed 10 months ago
docs: fix tool name mismatch and trailing commas in api.md example (#13559)
e1bdc23 Nhan Nguyen committed 10 months ago
docs: fix broken .md links and render issues (#13550)
18fdcc9 Vallabh Mahajan committed 11 months ago
llm: Avoid integer underflow on llama engine memory layout
172b592 Jesse Gross committed 11 months ago
Revert "Omit args and params in tool function def and calls (#13516)" (#13518)
522c11a Grace committed 11 months ago
types: add nested property support for tool definitions (#13508)
1c09403 Parth Sareen committed 11 months ago
parsers/renderers: use think from user for nemotron (#13492)
89eb795 Parth Sareen committed 11 months ago
fix: define GGML_VERSION variables for proper SOVERSION expansion (#13469)
aacd1cb Nhan Nguyen committed 11 months ago