Jagrit Digani
7f8ba2a003
[WIP] 2 pass sdpav
2025-08-06 09:56:39 -07:00
Jagrit Digani
c28249b81a
Add more nvtx range for debug
2025-08-06 09:56:39 -07:00
Jagrit Digani
e74bcdc5e3
Add sdpa file
2025-08-06 09:56:39 -07:00
Jagrit Digani
d8ed6c1aa3
Add base cudnn attention support
2025-08-06 09:56:39 -07:00
Awni Hannun
db5c7efcf6
revert default cuda install ( #2465 )
...
* revert default cuda install
* revert default cuda install
2025-08-06 06:19:12 -07:00
Awni Hannun
7bb96e4249
fix cublas on h100 ( #2466 )
2025-08-06 06:18:58 -07:00
Awni Hannun
fa89f0b150
faster gather qmm sorted test ( #2463 )
2025-08-05 06:27:40 -07:00
Awni Hannun
ca973d1e83
fix install tags ( #2464 )
2025-08-04 20:01:23 -07:00
Cheng
828c5f1137
Use SmallVector for shapes and strides ( #2454 )
...
* Use SmallVector for shapes and strides
* Convert SmallVector to tuple
2025-08-05 09:41:03 +09:00
Gaétan Lepage
7d86a5c108
Feat: add USE_SYSTEM_FMT CMake option ( #2219 )
2025-08-04 16:36:11 -07:00
Awni Hannun
0b807893a7
fix wraps compile ( #2461 )
2025-08-04 16:14:18 -07:00
Awni Hannun
6ad0889c8a
default install cuda on linux ( #2462 )
2025-08-04 15:33:05 -07:00
Zamderax
737dd6d1ac
Add missing <algorithm> header to jit_compiler.cpp ( #2460 )
...
Fixes compilation error on Linux where std::find_if is used on line 121
but the <algorithm> header was not included. While this might work on
some platforms due to transitive includes, it's not guaranteed by the
C++ standard.
Resolves issue #2459
2025-08-04 14:00:46 -07:00
Cheng
aaf78f4c6b
Use LRU cache for cuda graph ( #2448 )
...
* Use LRU cache for cuda graph
* Remove unused destructor
2025-08-02 21:28:57 +09:00
Angelos Katharopoulos
8831064493
Fix arctan2 grads ( #2453 )
2025-08-01 21:06:04 -07:00
Angelos Katharopoulos
be9bc96da4
[CUDA] Matmul utils initial commit ( #2441 )
2025-08-01 14:22:25 -07:00
Angelos Katharopoulos
86258f292f
[CUDA] Vectorize generated kernels ( #2444 )
2025-07-31 18:18:57 -07:00
Cheng
b26d88591c
[CUDA] Save primitive inputs faster ( #2449 )
...
* Add more nvtx loggings
* [CUDA] Saving primitive inputs faster
* Remove unneeded check
2025-08-01 10:16:06 +09:00
Cheng
86c6a15571
[CUDA] Backward convolution ( #2431 )
2025-08-01 09:54:05 +09:00
junpeiz
8b25ce62d5
Add tests for export including control flow models and quantized models ( #2430 )
...
* Add tests for export, including control flow export and quantized model export.
* Skip quantization related test for CUDA backend.
2025-07-31 11:06:26 -07:00
Awni Hannun
da5912e4f2
fix custom metal extension ( #2446 )
2025-07-31 06:25:36 -07:00
Cheng
daafee676f
Fix wrong graph key when using concurrent context ( #2447 )
2025-07-31 06:01:05 -07:00
Awni Hannun
d32519c8ee
fix gemv regression ( #2445 )
2025-07-30 14:23:01 -07:00
Awni Hannun
b405591249
fix circular reference ( #2443 )
2025-07-30 09:37:44 -07:00
Angelos Katharopoulos
3bf81ed1bd
[CUDA] Quantized refactoring ( #2442 )
2025-07-30 08:27:20 -07:00
Cheng
2204182bba
Make CI faster ( #2440 )
2025-07-30 02:26:36 -07:00
Cheng
3628e5d497
Use load_vector in arg_reduce ( #2439 )
2025-07-30 17:40:26 +09:00
Cheng
a0ae49d397
Move arange to its own file ( #2438 )
2025-07-30 13:05:51 +09:00
Cheng
254476718b
Remove the kernel arg from get_launch_args ( #2437 )
2025-07-30 11:43:02 +09:00
Awni Hannun
3adba92ebe
Cuda faster softmax ( #2435 )
...
* faster softmax and logsumexp
* faster softmax and logsumexp
* format
2025-07-29 17:18:12 -07:00
Awni Hannun
ef631d63af
faster rms norm ( #2433 )
2025-07-29 13:12:00 -07:00
Cheng
970dbe8e25
Use ccache in CI ( #2414 )
...
* Detect ccache
* Use ccache in CI
* Separate cache for different images
* Test both 12.2 and 12.9 for PRs
2025-07-29 08:43:22 +09:00
Awni Hannun
641be9463b
Add more CUDA architectures for PyPi package ( #2427 )
...
* add cuda sm 90
* add more archs
2025-07-28 12:35:15 -07:00
Awni Hannun
ab0e608862
[CUDA] More sizes for gemv ( #2429 )
...
* route more to gemv
* route more sizes to custom gemv
2025-07-28 12:35:01 -07:00
Awni Hannun
1588659062
no occupancy query for launch params ( #2426 )
2025-07-28 09:09:41 -07:00
Awni Hannun
b9e88fb976
[CUDA] Fix segfault on exit ( #2424 )
...
* fix cuda segfault on exit
* comment
2025-07-27 08:08:13 -07:00
Awni Hannun
4ad53414dd
fix cuda pypi package ( #2423 )
...
* fix cuda pypi package
* patch bump
2025-07-25 15:20:29 -07:00
Awni Hannun
d1165b215e
version ( #2420 )
2025-07-25 13:29:28 -07:00
Awni Hannun
dcb8319f3d
update install docs and requirements ( #2419 )
2025-07-25 12:13:19 -07:00
Awni Hannun
5597fa089c
Fix qvm splitk ( #2415 )
2025-07-25 11:50:24 -07:00
Awni Hannun
9acec364c2
[CUDA] Always use batched matmul ( #2404 )
...
* cuda batched mm
* addmm as well
* comment
2025-07-24 20:46:02 -07:00
Skonor
7d9d6ef456
docs: fix adam and adamw eps placement ( #2416 )
...
Co-authored-by: Mikhail Gorbunov <m_gorbunov@apple.com >
2025-07-24 16:40:45 -07:00
Cheng
6f5874a2f2
[CUDA] Initial implementation of Convolution with cuDNN ( #2385 )
...
* Link with cuDNN
* Initial implementation
* Remove backend apis
* Fix recording cudnn conv
* More unused backend apis
* Fix C++ conv tests
* include cudnn as python dep
* Install libcudnn9-dev-cuda-12 in CI
* cudnn only accepts contiguous inputs
* Switch to backend apis
* Plan needs to be kept alive
* Turn off tf32
* Add cache
* Test the native cuda graph api
* Set cudnn stream before execution
* Make LRUCache more like a normal container
* Do error check for cublas handle
* Zero-initilizing array
* Use tf32 for conv
* Skip TestConv.test_torch_conv_2D test
---------
Co-authored-by: Awni Hannun <awni@apple.com >
2025-07-25 08:12:10 +09:00
Awni Hannun
70dc336785
Test on cuda 12.2 and 12.9 ( #2413 )
2025-07-24 06:06:15 -07:00
Awni Hannun
4e504039f5
[Metal] Release metal events ( #2412 )
...
* release metal events
* fix
* fix
2025-07-23 19:53:42 -07:00
Awni Hannun
d1f4d291e8
Fix uv install and add dev release ( #2411 )
...
* fix uv install and add dev release
* fix docstring
* pin cuda deps
* cuda release on cpu-only machine
2025-07-23 16:54:19 -07:00
Awni Hannun
e1840853ce
full row mask in sdpa consistently gives nan ( #2406 )
2025-07-23 16:37:03 -07:00
Cheng
0f5ce173da
[CUDA] --compress-mode requires CUDA 12.8 ( #2407 )
2025-07-23 06:11:11 -07:00
Cheng
588854195f
Remove unused code in Convolution::vjp ( #2408 )
2025-07-23 06:11:00 -07:00
Fangjun Kuang
28d068bce6
Fix an error in the comment for mx.dequantize ( #2409 )
2025-07-23 06:10:50 -07:00
