https://airigs.net/topic/5/numa-aware-inference-with-lk_moe-lvllm-lsglang2026-09-28T16:25:26.530Zdaily0.6https://airigs.net/topic/6/vllm-with-mixed-quantization2026-09-28T16:30:26.067Zdaily0.6https://airigs.net/topic/7/rebar-alternatives-for-modified-gpus2026-09-28T16:36:56.555Zdaily0.6https://airigs.net/topic/8/exl32026-09-28T16:42:34.734Zdaily0.6https://airigs.net/topic/9/qwen-3.8-flash-next-on-rtx-3090-s2026-09-28T17:10:59.457Zdaily0.6https://airigs.net/topic/10/hardware-specs-website2026-09-30T15:48:21.075Zdaily0.6https://airigs.net/topic/11/stop-using-ollama-please.2026-09-30T16:04:51.886Zdaily0.6https://airigs.net/topic/12/modified-nvidia-gpus2026-09-30T16:13:05.297Zdaily0.6https://airigs.net/topic/13/strata-run-decent-models-on-small-hardware2026-09-30T16:17:25.493Zdaily0.6https://airigs.net/topic/14/new-to-local-ai-start-here2026-09-30T16:40:40.417Zdaily0.6https://airigs.net/topic/15/new-to-local-llms-start-here2026-09-30T17:19:42.657Zdaily0.6https://airigs.net/topic/16/what-s-an-moe-and-why-should-i-care2026-09-30T17:24:27.238Zdaily0.6https://airigs.net/topic/17/nanobot2026-09-30T17:27:06.977Zdaily0.6https://airigs.net/topic/39/8-bit-kv-cache-on-ampere2026-10-31T23:48:20.259Zdaily0.6https://airigs.net/topic/40/drafters-are-important2026-10-31T23:56:56.100Zdaily0.6