| .. |
|
cache
|
feat: support quantized inference (4-bit) for Gemma 3
|
2026-02-16 02:12:31 +00:00 |
|
model
|
fix: correct SDPA mask mode and slice logits to last position
|
2026-02-16 02:25:23 +00:00 |
|
sample
|
fix: remove unused vars in TopP sampler placeholder
|
2026-02-16 01:54:29 +00:00 |
|
tokenizer
|
fix: handle both string and array merge formats in tokenizer
|
2026-02-16 02:02:55 +00:00 |
|
array.go
|
fix: correct 20 mlx-c API mismatches for v0.4.1
|
2026-02-16 01:52:29 +00:00 |
|
CMakeLists.txt
|
chore: target macOS 26.0, fix duplicate -lstdc++ linker warning
|
2026-02-16 01:55:49 +00:00 |
|
compile.go
|
fix: correct 20 mlx-c API mismatches for v0.4.1
|
2026-02-16 01:52:29 +00:00 |
|
dtype.go
|
feat: add native MLX backend for Apple Silicon inference (pkg/mlx)
|
2026-02-16 01:19:04 +00:00 |
|
fast.go
|
fix: correct SDPA mask mode and slice logits to last position
|
2026-02-16 02:25:23 +00:00 |
|
io.go
|
feat: add native MLX backend for Apple Silicon inference (pkg/mlx)
|
2026-02-16 01:19:04 +00:00 |
|
mlx.go
|
debug: add shape logging and stderr error handler for inference debugging
|
2026-02-16 02:16:30 +00:00 |
|
mlx_stub.go
|
feat: add native MLX backend for Apple Silicon inference (pkg/mlx)
|
2026-02-16 01:19:04 +00:00 |
|
nn.go
|
feat: support quantized inference (4-bit) for Gemma 3
|
2026-02-16 02:12:31 +00:00 |
|
ops.go
|
fix: use affine quantization mode and infer head_dim from weights
|
2026-02-16 02:19:33 +00:00 |
|
random.go
|
fix: correct 20 mlx-c API mismatches for v0.4.1
|
2026-02-16 01:52:29 +00:00 |
|
slice.go
|
fix: correct 20 mlx-c API mismatches for v0.4.1
|
2026-02-16 01:52:29 +00:00 |
|
stream.go
|
feat: add native MLX backend for Apple Silicon inference (pkg/mlx)
|
2026-02-16 01:19:04 +00:00 |
