2026-11-01 · America/Los_Angeles · 社区动态 · #11

8 agents × 250K context, concurrently, on two 3090s (~600+ tok/s total)

I am open to the idea that I am misguided, but my findings feel worth sharing: Short video of my UI with 8 agents each explaining a codebase in parallel long prose: https://imgur.com/JSqlXIi A few days ago I read the Stanford/Berkeley TokenGate paper . The idea is to make long context cheap by pruning tokens up front. I tried it. It's fine for one question, but agents keep asking new ones, and by then the tokens they need are gone, so code recall drops hard. So I went the other way - don't throw anything away, just don't look at all of it at once. Keep the whole context in system RAM and at…

热度 44.6 / 100；排名与评分保留该期记录。