llama.cpp b10956

sycl: rfc: Use radix select for top_k ( #28670 ) sycl: GPU-resident TOP_K for large k, parallelised over the device The SYCL backend refused GGML_OP_TOP_K…

sycl: rfc: Use radix select for top_k ( #28670 ) sycl: GPU-resident TOP_K for large k, parallelised over the device The SYCL backend refused GGML_OP_TOP_K above k = 32 and let it fall back to the CPU, a backend round-trip per call. The limit was not conservatism: the scan-merge…

Read the original source — github.com

release · Shared by tscosj

0 comments

No comments yet.