server: add router device memory margin parameter for dynamic unloading (#21231)
* server: add --models-memory-max parameter to allow dynamically unloading models when they exceed a memory size threshold
estimate with to-be-loaded model size included
use no_alloc to get memory requirements for model load
only set model memory_mb if not previously calculated
use memory margin instead of total size limit, apply to each device separately
add server memory debug logging
move llama_context_device_memory function to llama-ext.h
fix model count exceeded check
improve memory_per_device map naming
improve variable naming, fix style
also strip models memory margin from child processes
cont : clean-up
replace device memory map with buft memory map. Use llama_get_memory_breakdown
extract duplicated check into helper function
move model memory estimation to subprocess
precompute name->buft map, map GPU host types to CPU buft
cleanup unused variable
remove duplicated init calls
* adapt to upstream changes
* wip
* common_memory_reports internface
* SERVER_ROLE_MEASURE
* server-models-sched
* fix build
* server : fix memory accounting of measure children and claim spin
A measure child runs no_alloc, so the free memory it reports does not
include its estimate: subtracting self there erased the memory held by
other processes, down to zero with --fit on, and the next load could
overshoot the margin. Subtract self only for instance reports.
A queued load only checked --models-max before claiming, so when the
memory margin blocked it behind a busy model, load() threw and the
waiter retried in a tight loop. Refuse the claim while the limits are
exceeded and no idle model can be unloaded, so the waiter sleeps on
the condition variable until one goes idle.
---------
Co-authored-by: Xuan Son Nguyen
Co-authored-by: Pascal
**Website:**
-
**Attestations:**
-
**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-macos-arm64.tar.gz)
- macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780)
- [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-xcframework.zip)
**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-ubuntu-cuda-12.8-x64.tar.gz) - [CUDA 12.8 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b11930/cudart-llama-b11930-bin-ubuntu-cuda-12.8-x64.tar.gz)
- [Ubuntu x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-ubuntu-cuda-13.4-x64.tar.gz) - [CUDA 13.4 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b11930/cudart-llama-b11930-bin-ubuntu-cuda-13.4-x64.tar.gz)
- [Ubuntu arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-ubuntu-cuda-13.4-arm64.tar.gz) - [CUDA 13.4 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b11930/cudart-llama-b11930-bin-ubuntu-cuda-13.4-arm64.tar.gz)
- [Ubuntu x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-ubuntu-rocm-10.0-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-ubuntu-openvino-2026.4.1-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-ubuntu-sycl-fp16-x64.tar.gz)
- [Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-linux-arm64-snapdragon.tar.gz) - [setup guide](https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/linux.md)
**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-android-arm64.tar.gz)
- [Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-android-arm64-snapdragon.tar.gz) - [setup guide](https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/README.md)
**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-win-cpu-arm64.zip)
- [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-win-opencl-adreno-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b11930/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-win-cuda-13.4-x64.zip) - [CUDA 13.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b11930/cudart-llama-bin-win-cuda-13.4-x64.zip)
- [Windows arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-win-cuda-13.4-arm64.zip) - [CUDA 13.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b11930/cudart-llama-bin-win-cuda-13.4-arm64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-win-vulkan-x64.zip)
- [Windows arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-win-vulkan-arm64.zip)
- [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-win-openvino-2026.4.1-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-win-sycl-x64.zip)
- [Windows x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-bin-win-rocm-10.0-x64.zip)
**openEuler:**
- [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23705)
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
**UI:**
- [UI](https://github.com/ggml-org/llama.cpp/releases/download/b11930/llama-b11930-ui.tar.gz)