Files
ollama/llm
saman-amdandGitHub 15af2b261c llm: keep weights out of pinned host memory on Windows iGPUs (#19636)
On Windows, pinned host memory for an integrated GPU is charged to the
same WDDM shared-memory budget as its device buffers. llama-server turns
off mmap for iGPUs and places CPU-side weights in pinned host memory,
which --fit does not count, so a partially offloaded model overflows the
budget and the KV cache allocation fails. Pass --no-host for Windows
iGPUs so CPU-side weights stay in pageable memory.
2026-11-15 10:46:15 -08:00
..
…
2026-10-27 08:47:18 -07:00
2026-09-22 13:58:49 -07:00