AirLLM 2.8T LLM inference with single 4GB GPU
Python chinese-llmchinese-nlpfinetunegenerative-aiinstruct-gptinstruction-setllamallmloraopen-modelsopen-sourceopen-source-modelsqlora
Commits on main
feat: support Kimi K3 (2.8T MXFP4 multimodal MoE) and fix streaming gaps it exposed
2decbfd Yu Li committed 3 months ago
fix(ci): use collaborator PAT for star history stargazers fetch
e57c381 Yu Li committed 4 months ago