Skip to content

cuda: GGML_CUDA_FA_PREFILL_F16=N, f16 prefill for quantized K/V from pool memory (decode stays in place) - #330

Open
professorpalmer wants to merge 1 commit into
PrismML-Eng:prismfrom
professorpalmer:claude/fa-prefill-f16-pool
Open

cuda: GGML_CUDA_FA_PREFILL_F16=N, f16 prefill for quantized K/V from pool memory (decode stays in place)#330
professorpalmer wants to merge 1 commit into
PrismML-Eng:prismfrom
professorpalmer:claude/fa-prefill-f16-pool

cuda: GGML_CUDA_FA_PREFILL_F16=N converts a quantized K/V cache of up…

066e3e3
Select commit
Loading
Failed to load commit list.
Sign in for the full log view

Annotations

1 warning
labeler
succeeded Oct 7, 2026 in 31s