CERBERUS/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-10 01:41:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
ollama/x/mlxrunner/mlx
History
Exact
Daniel Hiltgen 630882621b
llama-server followups (#16353) 
* 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
2026-06-01 10:44:21 -07:00
..
generator ci: Fix windows build (#14754) 2026-03-09 19:27:59 -07:00
include/mlx/c Update MLX and MLX-C with threading fixes (#15845) 2026-05-03 10:03:14 -07:00
.gitignore Add MLX runner with GLM4-MoE-Lite model support (#14185) 2026-02-10 14:57:57 -08:00
act.go New models (#15861) 2026-04-28 11:50:12 -07:00
array.go mlx: improve thread safety of array management 2026-04-21 14:38:49 -07:00
array_test.go mlx: Gemma4 MTP speculative decoding (#15980) 2026-05-05 08:55:04 -07:00
CMakeLists.txt mlx: update as of 3/23 (#14789) 2026-03-23 11:28:44 -07:00
compile.go mlx: improve thread safety of array management 2026-04-21 14:38:49 -07:00
compile_test.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
dtype.go MLX: add header vendoring and remove go build tag (#14642) 2026-03-09 17:24:45 -07:00
dynamic.c mlx: remove noisy error output from dynamic library loading (#14346) 2026-02-20 23:46:07 -08:00
dynamic.go llama-server followups (#16353) 2026-06-01 10:44:21 -07:00
dynamic.h MLX: add header vendoring and remove go build tag (#14642) 2026-03-09 17:24:45 -07:00
dynamic_darwin.go mlx: Improve M5 performance with NAX (#15345) 2026-04-07 08:12:24 -07:00
dynamic_other.go mlx: Improve M5 performance with NAX (#15345) 2026-04-07 08:12:24 -07:00
fast.go mlxrunner: decouple models from attention cache storage layout 2026-04-27 20:04:46 -07:00
gated_delta.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
generated.c Update MLX and MLX-C with threading fixes (#15845) 2026-05-03 10:03:14 -07:00
generated.h Update MLX and MLX-C with threading fixes (#15845) 2026-05-03 10:03:14 -07:00
io.go mlx: Support NVIDIA TensorRT Model Optimizer import (#15566) 2026-04-27 18:28:10 -07:00
memory.go MLX: add header vendoring and remove go build tag (#14642) 2026-03-09 17:24:45 -07:00
mlx.go mlx: add compiled closure support 2026-04-14 16:38:32 -07:00
nn.go mlx: improve thread safety of array management 2026-04-21 14:38:49 -07:00
ops.go mlx: Gemma4 MTP speculative decoding (#15980) 2026-05-05 08:55:04 -07:00
ops_extra.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
random.go mlx: rework the MLX sampler (#16122) 2026-05-13 17:18:27 -07:00
slice.go mlxrunner: fix Slice(0, 0) returning full dimension instead of empty 2026-03-18 16:06:33 -07:00
stream.go Update MLX and MLX-C with threading fixes (#15845) 2026-05-03 10:03:14 -07:00
thread_test.go Update MLX and MLX-C with threading fixes (#15845) 2026-05-03 10:03:14 -07:00