| # | Наименование новости | Тональность | Информативность | Дата публикации |
|---|---|---|---|---|
| 1 | TileRT - Tile-Based Runtime for Ultra-Low-Latency LLM Inference | 0 | 35 | 28-06-2026 |
| 2 | omlx - LLM inference server | 0 | 10 | 06-04-2026 |
| 3 | whichllm - поиск лучшей LLM модели под оборудование | 0 | 10 | 08-06-2026 |
| 4 | Memori - SQL Native Memory Layer for LLM | 0 | 10 | 27-12-2025 |
| 5 | Semantic Caching for LLMs: FastAPI, Redis, and Embeddings | 0 | 10 | 29-04-2026 |
| 6 | WeDLM - diffusion language model | 0 | 10 | 24-01-2026 |
| 7 | chunkhound - Local first codebase intelligence | 0 | 10 | 24-01-2026 |
| 8 | Using LLMs to find Python C-extension bugs | 0 | 24.29 | 26-04-2026 |
| 9 | loki-mode - Multi-agent provider agnostic framework | 0 | 43.33 | 15-02-2026 |
| 10 | AI-research-SKILLs - library of AI skills | 0 | 26.67 | 17-01-2026 |