github-actions[bot] Bot released b10241 of ggml-org/llama.cpp · August 3, 2026 07:58 ggml-org / /ggml-org/llama.cpp b10241 CUDA: Fix data-races when reusing SMEM in block_reduce (#26385)CUDA: Fix data-races when reusing block_reduceblock_reduce currently doesn't resync after reading from SMEM, causingpotential da… Read more Contributors