mirror of
https://github.com/ollama/ollama.git
synced 2026-08-04 14:56:15 +00:00
a6293eb516
* llm: allow iGPU mmproj offload with fit padding llama.cpp's fit pass sizes text-model placement before the multimodal projector is loaded. Ollama had been avoiding that risk on non-Metal iGPUs by disabling projector offload entirely, which forces CLIP onto CPU on GB10 and Strix Halo even when the projector has ample memory available. Let integrated GPUs use the same projector-memory check as other GPUs. When projector offload is enabled, add the estimated projector memory plus the existing 1 GiB headroom to Ollama-owned LLAMA_ARG_FIT_TARGET so fit leaves space for the later projector allocation. If Ollama/device setup already supplied a fit target, add the projector pad to it. If the user set LLAMA_ARG_FIT_TARGET explicitly, leave it exactly as provided. Fixes #16419 * review comments |
||
|---|---|---|
| .. | ||
| exit_status.go | ||
| exit_status_other.go | ||
| exit_status_windows.go | ||
| llama_binary.go | ||
| llama_binary_test.go | ||
| llama_server.go | ||
| llama_server_test.go | ||
| llm_darwin.go | ||
| llm_linux.go | ||
| llm_windows.go | ||
| media.go | ||
| metal_retry.go | ||
| rocm_default.go | ||
| rocm_windows.go | ||
| server.go | ||
| server_wait_test.go | ||
| status.go | ||
| status_test.go | ||
| vulkan_windows.go | ||