CERBERUS/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-10-21 02:51:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
ollama/mlx
History
Exact
Daniel Hiltgen c0f8da35b2
mlx: speed up Qwen 3.8 prompt processing (#18550) 
* mlx: speed up Qwen 3.8 prompt processing

Use MLX's gated-delta kernel for long scans and fold dense MLP global scales into SwiGLU.

* address comments
2026-09-22 17:53:23 -07:00
..
compat/mlx-c MLX: version bump (#18576) 2026-09-22 17:13:16 -07:00
generator mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
include/mlx/c MLX: version bump (#18576) 2026-09-22 17:13:16 -07:00
mlxtest mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
mlxthread mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
quant mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
.gitignore mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
act.go mlx: speed up Qwen 3.8 prompt processing (#18550) 2026-09-22 17:53:23 -07:00
act_test.go mlx: speed up Qwen 3.8 prompt processing (#18550) 2026-09-22 17:53:23 -07:00
array.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
array_test.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
CMakeLists.txt mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
compile.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
compile_test.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
depthwise_conv.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
depthwise_conv_test.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
dtype.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
dynamic.c mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
dynamic.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
dynamic.h mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
dynamic_darwin.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
dynamic_other.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
fast.go MLX: version bump (#18576) 2026-09-22 17:13:16 -07:00
fast_gated_delta_test.go MLX: version bump (#18576) 2026-09-22 17:13:16 -07:00
gated_delta.go mlx: speed up Qwen 3.8 prompt processing (#18550) 2026-09-22 17:53:23 -07:00
gated_delta_test.go mlx: speed up Qwen 3.8 prompt processing (#18550) 2026-09-22 17:53:23 -07:00
generated.c MLX: version bump (#18576) 2026-09-22 17:13:16 -07:00
generated.h MLX: version bump (#18576) 2026-09-22 17:13:16 -07:00
gpu_kernel.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
io.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
io_test.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
kernel_test.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
mamba2_scan.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
mamba_kernels_test.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
memory.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
memory_test.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
mlx.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
nn.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
ops.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
ops_extra.go mlx: speed up Qwen 3.8 prompt processing (#18550) 2026-09-22 17:53:23 -07:00
ops_extra_test.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
random.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
scope.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
scope_test.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
slice.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
stream.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00
thread_test.go mlx, mlxrunner: move the MLX engine out of x/ 2026-09-16 14:06:08 -07:00