ollama/discover
Daniel Hiltgen 73ee71ddcc
mlxrunner: adapt saved history to memory pressure (#19678)
* mlxrunner: adapt saved history to memory pressure

Retain Metal prefix history using observed memory headroom and execution
workspace rather than a fixed 8 GiB allowance. Release unused buffers and
cold history when system compression grows, preserving reusable paths and
active requests.

Cover pressure reclamation, snapshot ownership, memory observation, and
cacheless request isolation.

* address comments

* address comments
2026-11-19 15:41:42 -08:00
..
amd.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
amd_test.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
cpu_linux.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
cpu_windows.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
cuda_compat.go CUDA: require driver 550 or newer for v12 (#16895) 2026-06-25 08:46:00 -07:00
cuda_compat_test.go CUDA: require driver 550 or newer for v12 (#16895) 2026-06-25 08:46:00 -07:00
gpu.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
gpu_darwin.go mlxrunner: adapt saved history to memory pressure (#19678) 2026-11-19 15:41:42 -08:00
gpu_darwin_test.go mlxrunner: adapt saved history to memory pressure (#19678) 2026-11-19 15:41:42 -08:00
gpu_info_darwin.h mlxrunner: adapt saved history to memory pressure (#19678) 2026-11-19 15:41:42 -08:00
gpu_info_darwin.m mlxrunner: adapt saved history to memory pressure (#19678) 2026-11-19 15:41:42 -08:00
host_memory.go mlxrunner: adapt saved history to memory pressure (#19678) 2026-11-19 15:41:42 -08:00
llama_server.go Clean up dead code (#17381) 2026-08-27 14:33:51 -07:00
llama_server_test.go Clean up dead code (#17381) 2026-08-27 14:33:51 -07:00
memory_darwin.go mlxrunner: adapt saved history to memory pressure (#19678) 2026-11-19 15:41:42 -08:00
memory_darwin_test.go mlxrunner: adapt saved history to memory pressure (#19678) 2026-11-19 15:41:42 -08:00
memory_headroom.go mlxrunner: adapt saved history to memory pressure (#19678) 2026-11-19 15:41:42 -08:00
memory_headroom_test.go mlxrunner: adapt saved history to memory pressure (#19678) 2026-11-19 15:41:42 -08:00
native_probe.go lint fixes (#17897) 2026-08-20 10:23:25 -07:00
native_probe_linux.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
native_probe_linux_nocgo.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
native_probe_platform.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
native_probe_stub.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
native_probe_test.go discover: fix inverted iGPU/dGPU Vulkan classification on Windows hybrid graphics (#16669) 2026-06-22 14:52:03 -07:00
native_probe_windows.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
runner.go discover: fall back to standard CUDA when the JetPack runner is absent (#16949) 2026-07-02 08:34:35 -07:00
runner_test.go discover: allow Radeon 8060S iGPU by default (#16429) 2026-06-02 11:15:01 -07:00
types.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
vulkan.go discover: fix inverted iGPU/dGPU Vulkan classification on Windows hybrid graphics (#16669) 2026-06-22 14:52:03 -07:00
vulkan_refine_stub.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
vulkan_refine_windows.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00