Dio Fu

[Dio Fu @fubyo]

@xYurimax @spiritbuun i am on Windows 10, similar args. also same performance :-S

[Dio Fu @fubyo]

@spiritbuun maybe I can get it up to 0.2-0.3 , if I tell the model to repeat stuff.

[Dio Fu @fubyo]

@spiritbuun Nice! My acceptance rate hovers around 0.1 . Any ideas? here is how I run it: buun-llama-cpp/build/bin/Release/llama-server.exe -m Qwen3.6-27B-Q4_K_M.gguf -md dflash-draft-3.6-q8_0.gguf --spec-type dflash -c 196608 -cd 16536 --cache-type-k turbo3_tcq --cache-type-v turbo3_tcq

[Dio Fu @fubyo]

@pupposandro Megakernel 27B + DFlash + TurboCache, and we feast in Valhalla.

[Dio Fu @fubyo]

@pupposandro turboquant in there too someday? can the draft model also get quantized to make room for more context?

[Dio Fu @fubyo]

@Ali_TongyiLab anything audio related?

[Dio Fu @fubyo]

@RedCollie1 What if the rod was curved with its two ends coming together forming a ring?

[Dio Fu @fubyo]

@trutharmyfilms 182,687,495

[Dio Fu @fubyo]

@PhoenixWallet @SatCastle21 Splicing funds in seems to require 2 on-chain transactions (the original transaction from another wallet and the actual splice-in). How is this better than doing a swap-in (in case there is enough incoming liquidity) ? Could that be improved ?