Local Ai
b9413
Release b9413 includes a CUDA fix that checks PTX version on the host side to guard PDL dispatch, addressing an issue where incorrect dispatching could occur on newer GPU architectures like sm_90/sm_1
Release b9413 includes a CUDA fix that checks PTX version on the host side to guard PDL dispatch, addressing an issue where incorrect dispatching could occur on newer GPU architectures like sm_90/sm_120 in forward-JIT mode. The release also adds support for the DeepSeek V3.2 model family with DSA lightning indexer.
Source: llama.cpp Releases | 2026-05-29