upstream-archive/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-23 09:10:53 -05:00
Code Issues Packages Projects Releases Wiki Activity

llama-server followups (#16353)

Browse Source 
* llama-server followups

Misc fixes for #16031
- Add back dropped ROCm build flag for multi-GPU support on windows
- Fix amdhip64_*.dll version detection for "latest" selection
- Fix embeddings API for consistent normalize behavior with prior versions

* ci: set up for automated llama.cpp update testing

* reduce batch for fa-disabled, and constrained vram

* mlx: fix v3 load bug on m5

Imagegen was incorrectly loading v3 first.  This DRYs out the loading code so imagegen gets the same new v4/v3 selection logic.

* fix reload bug on embedding models

* bump version

* steer user how to enable iGPU when disabled
This commit is contained in:
Daniel Hiltgen
2026-06-01 10:44:21 -07:00
committed by GitHub
parent 0e93ccc2cd
commit 630882621b
15 changed files with 967 additions and 158 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
cmake/local.cmake
View File

@@ -575,6 +575,7 @@ if(OLLAMA_HAVE_LLAMA_SERVER)
ollama_append_cache_arg_if_set(_rocm_args AMDGPU_TARGETS)
ollama_append_cache_arg_if_set(_rocm_args CMAKE_HIP_ARCHITECTURES)
ollama_append_cache_arg_if_set(_rocm_args CMAKE_HIP_FLAGS)
ollama_append_cache_arg_if_set(_rocm_args GGML_CUDA_NO_PEER_COPY)
ollama_append_cache_arg_if_set(_rocm_args CMAKE_PREFIX_PATH)
ollama_add_llama_server_build(${_backend}
PRESET ${_rocm_preset}