Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
tools: relax JSON parse constraints for tool calling (#10872)
066d0f4 Parth Sareen committed 1 year ago
readme: add AWS Strands Agents SDK example to community integrations (#10865)
012cf65 RAPID ARCHITECT committed 1 year ago
server: add hint to the error message when model path access fails (#10843)
eda472d frob committed 1 year ago
tools: refactor tool call parsing and enable streaming (#10415)
e8b981f Parth Sareen committed 1 year ago
ml: Panic rather than return error on tensor allocation failure
1f371ea Jesse Gross committed 1 year ago
server: improve tensor quantization fallback logic (#10806)
fbe6ae2 Bruce MacDonald committed 1 year ago
remove support for multiple ggufs in a single file (#10722)
61aeaf7 Michael Yang committed 1 year ago
fix: qwen25vl assign samebatch in multimodal input (#10789)
69b2fe9 Michael Yang committed 1 year ago
llama: fix incorrect initialization of C.struct_common_sampler_cparams.penalty_present (#10779)
e6a800c DarkCaster committed 1 year ago