ai
์ด 9๊ฐ์ ์ํค ยท 1 / 1 ํ์ด์ง ๐ก RSS ๐ธ๏ธ ๊ทธ๋ํ
- [LLM Eval] HELM: Holistic Evaluation of Language Models#ai #llm #evaluation #benchmark
- Function Calling / Tool Use: LLM ๋๊ตฌ ์ฌ์ฉ#ai #llm #function-calling #agent
- LLM RAG: Retrieval-Augmented Generation#ai #llm #rag #retrieval
- [Voice AI] Agent ํจํด: Supervisor, Handoff, ReAct, HITL#agent #multi-agent #supervisor #handoff #react #hitl
- [Voice AI] LLM Serving: vLLM, PagedAttention, continuous batching#llm-serving #vllm #paged-attention #kv-cache #ttft
- [Voice AI] Pipecat vs LiveKit Agents: ํ๋ ์์ํฌ ๋น๊ต#pipecat #livekit #voice-framework #agent #sfu
- [Voice AI] Voice RAG: ์ง์ฐ ๋ณ๋ชฉ + ์์ธก์ ํ๋ฆฌํ์น#voice-rag #rag #vector-db #latency #prefetch
- [Voice AI] ์์ฑ ์์ด์ ํธ ์ํคํ ์ฒ: Cascading / Streaming / S2S + Latency Budget#voice-agent #architecture #latency #streaming #cascading #s2s
- [Voice AI] ์์ฑ ์ฐ์ ํ๋กฌํํธ + Function Calling + Structured Output#prompt #function-calling #structured-output #voice-llm