cturan/llama.cpp

Mirror von https://github.com/cturan/llama.cpp

Autor	SHA1 Nachricht	Datum
0cc4m	dcb2ed4826 OpenCL: Fix duplication of layers in VRAM and RAM, add GPU mul kernel (#1653)	vor 2 Jahren
Howard Su	bb051d9723 opencl : no need to allocate cl_mem on heap (#1612)	vor 2 Jahren
Howard Su	ca74884f66 opencl : use strstr to check if fp16 supported (#1611)	vor 2 Jahren
Maarten ter Huurne	7d873811f3 Fix handling of "invalid property" when creating OpenCL command queue (#1565)	vor 2 Jahren
0cc4m	2e6cd4b025 OpenCL Token Generation Acceleration (#1459)	vor 2 Jahren