Awni Hannun a54f06b16f Fast RMS Norm (#862) ...

* fast rmsnorm

* no rms gpu

* kernel

* fix shared mem

* looped rms and donation in softmax

* Make the squaring in float32 to avoid underflow

* Fix the default StreamOrDevice for rope and rms_norm in fast

* nits

---------

Co-authored-by: Angelos Katharopoulos <a_katharopoulos@apple.com>

2024-03-21 07:20:54 -07:00

..

mlx_tests.py

Buffer Donation (#519)

2024-01-26 16:30:33 -08:00

test_array.py

Switch to nanobind (#839)

2024-03-18 20:12:25 -07:00

test_autograd.py

Fix logsumexp edge case (#740)

2024-02-25 08:39:55 -08:00

test_bf16.py

bump pre commit and fix format (#373)

2024-01-04 16:28:52 -08:00

test_blas.py

No copy gems (#801)

2024-03-12 13:13:41 -07:00

test_compile.py

NumberOfElements for shapeless compile and vmap fixes (#802)

2024-03-13 10:34:14 -07:00

test_constants.py

feat: Add numpy constants (#428)

2024-01-11 06:47:29 -08:00

test_conv.py

Convolution update (#651)

2024-02-28 20:11:16 -08:00

test_device.py

Adds device context manager (#679)

2024-02-14 14:14:58 -08:00

test_eval.py

Compile with capture (#629)

2024-02-07 17:29:22 -08:00

test_fast_sdpa.py

Fix test (#785)

2024-03-04 23:02:27 -08:00

test_fast.py

Fast RMS Norm (#862)

2024-03-21 07:20:54 -07:00

test_fft.py

Adds device context manager (#679)

2024-02-14 14:14:58 -08:00

test_graph.py

Multi output primitives (#330)

2024-01-08 16:39:08 -08:00

test_init.py

Make shape a tuple (#591)

2024-01-30 13:11:01 -08:00

test_linalg.py

Add matrix inversion primitive (#822)

2024-03-15 06:34:36 -07:00

test_load.py

Fix logsumexp edge case (#740)

2024-02-25 08:39:55 -08:00

test_losses.py

Feat: Add weights argument in BCE Loss and tests (#620)

2024-02-07 09:39:52 -08:00

test_metal.py

bindings for memory info (#761)

2024-03-01 19:51:58 -08:00

test_nn.py

fix modules with dict (#819)

2024-03-12 08:54:06 -07:00

test_ops.py

Check edge case handling in row reduce med kernel (#858)

2024-03-20 11:37:58 -07:00

test_optimizers.py

Some fixes in cache / thread safety (#777)

2024-03-05 13:30:50 -08:00

test_quantized.py

Quantized matmul fix (#677)

2024-02-12 18:54:21 -08:00

test_random.py

Add loc and scale to random.normal (#638)

2024-02-07 11:49:59 -08:00

test_reduce.py

Add GPU support for uint64/int64 reductions (#569)

2024-01-31 11:18:04 -08:00

test_tree.py

Add isort pre-commit and run (#68)

2023-12-08 11:31:47 -08:00

test_vmap.py

vmap matmul and admm (#836)

2024-03-14 14:38:22 -07:00