qazal 8feb8edc68 gemm/asm: add fp8 support to cdna asm_gemm (#15542) ...

* work

* hmm, mixins

* rhs_transposed

* also fix the dtype

* check for hipcc

* Exception

* select dev

* default

2026-03-31 19:32:54 +09:00

..

__init__.py

move tests to test/backend (#14691)

2026-02-12 11:09:44 +08:00

test_arange.py

embedded bwd vocab shard (#15001)

2026-03-16 19:37:16 -07:00

test_asm_gemm.py

gemm/asm: add fp8 support to cdna asm_gemm (#15542)

2026-03-31 19:32:54 +09:00

test_const_folding.py

fix copying padded const (#15116)

2026-03-04 10:39:45 +08:00

test_custom_kernel.py

reduce mixin (#15523)

2026-03-30 05:23:58 -04:00

test_dtype_alu.py

automatically emulate unsupported (tiny) floats [skip_process_replay] (#15366)

2026-03-20 02:31:44 -04:00

test_dtype.py

deprecate <dev>=1 in favor of DEV=<dev> (#15467)

2026-03-26 03:48:03 -04:00

test_edgecases.py

move tests to test/backend (#14691)

2026-02-12 11:09:44 +08:00

test_graph.py

jit: graphing in uops (#15489)

2026-03-27 19:09:02 +03:00

test_image_dtype.py

remove IMAGE=2 (#15312)

2026-03-20 06:26:52 -04:00

test_interop.py

move tests to test/backend (#14691)

2026-02-12 11:09:44 +08:00

test_jit_cases.py

move tests to test/backend (#14691)

2026-02-12 11:09:44 +08:00

test_jit_footguns.py

jit: fix raw in same kernel (#14699)

2026-02-12 15:33:32 +03:00

test_jit.py

jit: graphing in uops (#15489)

2026-03-27 19:09:02 +03:00

test_kernel_cache.py

move tests to test/backend (#14691)

2026-02-12 11:09:44 +08:00

test_linearizer_dumb.py

dtypes.index -> dtypes.weakint (#15377)

2026-03-20 01:08:46 -04:00

test_linearizer.py

move test_grouped_dims to test/null (#14893)

2026-02-19 14:50:53 -05:00

test_multitensor.py

llama compute gradients explicitly + 243 GB of RAM on MP=8 (#15343)

2026-03-18 19:54:40 +08:00

test_nn.py

move tests to test/backend (#14691)

2026-02-12 11:09:44 +08:00

test_ops.py

deprecate <dev>=1 in favor of DEV=<dev> (#15467)

2026-03-26 03:48:03 -04:00

test_opt_gemm.py

move tests to test/backend (#14691)

2026-02-12 11:09:44 +08:00

test_optim.py

move tests to test/backend (#14691)

2026-02-12 11:09:44 +08:00

test_pickle.py

update test to reset and test kernel_count directly (#14832)

2026-02-17 11:48:46 -05:00

test_profiler.py

jit: graphing in uops (#15489)

2026-03-27 19:09:02 +03:00

test_quantize_onnx.py

remove staticmethod dtypes.max/min (#15227)

2026-03-11 23:11:24 -04:00

test_randomness.py

feat: no if in rand (#15333)

2026-03-18 15:09:51 -07:00

test_rangeify.py

move tests to test/backend (#14691)

2026-02-12 11:09:44 +08:00

test_renderer_failures.py

remove staticmethod dtypes.max/min (#15227)

2026-03-11 23:11:24 -04:00

test_schedule.py

remove IMAGE=2 (#15312)

2026-03-20 06:26:52 -04:00

test_setitem.py

fix Invalid combine rules (#15345)

2026-03-18 04:58:02 -04:00

test_softmax_fusion.py

move tests to test/backend (#14691)

2026-02-12 11:09:44 +08:00

test_stunning.py

raise RuntimeError in schedule for conflicted var_val [pr] (#15031)

2026-02-26 15:16:01 -05:00

test_subbuffer.py

buffer view is like buffer (#15082)

2026-03-03 09:52:33 +08:00

test_symbolic_jit.py

allocate generates a call (#14958)

2026-02-23 15:59:20 +08:00

test_symbolic_ops.py

Support triu variable on diagonal + SDPA symbolic (#15081)

2026-03-02 12:19:48 +08:00

test_tensor_variable.py

Support triu variable on diagonal + SDPA symbolic (#15081)

2026-03-02 12:19:48 +08:00

test_tensor.py

failed test case for Tensor(np, "bf16") (#15358)

2026-03-18 23:40:14 -04:00

test_to_numpy.py

move tests to test/backend (#14691)

2026-02-12 11:09:44 +08:00

test_transcendental.py

deprecate <dev>=1 in favor of DEV=<dev> (#15467)

2026-03-26 03:48:03 -04:00

test_uops.py

deprecate <dev>=1 in favor of DEV=<dev> (#15467)

2026-03-26 03:48:03 -04:00

test_zero_copy.py

move tests to test/backend (#14691)

2026-02-12 11:09:44 +08:00