| .. |
|
backend.py
|
feat(mlx): add thread-safe LRU prompt cache and min_p/top_k sampling (#7556)
|
2025-12-16 11:27:46 +01:00 |
|
install.sh
|
feat(mlx): add mlx backend (#6049)
|
2025-08-22 08:42:29 +02:00 |
|
Makefile
|
feat(mlx): add mlx backend (#6049)
|
2025-08-22 08:42:29 +02:00 |
|
mlx_cache.py
|
feat(mlx): add thread-safe LRU prompt cache and min_p/top_k sampling (#7556)
|
2025-12-16 11:27:46 +01:00 |
|
requirements-cpu.txt
|
feat(mlx): Add support for CUDA12, CUDA13, L4T, SBSA and CPU (#8380)
|
2026-02-03 23:53:34 +01:00 |
|
requirements-cublas12.txt
|
feat(mlx): Add support for CUDA12, CUDA13, L4T, SBSA and CPU (#8380)
|
2026-02-03 23:53:34 +01:00 |
|
requirements-cublas13.txt
|
feat(mlx): Add support for CUDA12, CUDA13, L4T, SBSA and CPU (#8380)
|
2026-02-03 23:53:34 +01:00 |
|
requirements-l4t12.txt
|
feat(mlx): Add support for CUDA12, CUDA13, L4T, SBSA and CPU (#8380)
|
2026-02-03 23:53:34 +01:00 |
|
requirements-l4t13.txt
|
feat(mlx): Add support for CUDA12, CUDA13, L4T, SBSA and CPU (#8380)
|
2026-02-03 23:53:34 +01:00 |
|
requirements-mps.txt
|
feat(mlx): add mlx backend (#6049)
|
2025-08-22 08:42:29 +02:00 |
|
requirements.txt
|
feat(mlx): add mlx backend (#6049)
|
2025-08-22 08:42:29 +02:00 |
|
run.sh
|
feat(mlx): add mlx backend (#6049)
|
2025-08-22 08:42:29 +02:00 |
|
test.py
|
feat(mlx): add thread-safe LRU prompt cache and min_p/top_k sampling (#7556)
|
2025-12-16 11:27:46 +01:00 |
|
test.sh
|
feat(mlx): add mlx backend (#6049)
|
2025-08-22 08:42:29 +02:00 |
|
test_mlx_cache.py
|
feat(mlx): add thread-safe LRU prompt cache and min_p/top_k sampling (#7556)
|
2025-12-16 11:27:46 +01:00 |
