qazalandGitHub 7dd3422c63 llama: replace two stage amax with atomics (#17063) ...

* atomic amax in c kernels

* quantize fp8 UOp kernel

* diff

2026-07-17 19:27:10 +09:00

..

__init__.py

move tests to test/backend (#14691)

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

test_arange.py

skip test_index_fused_out_of_bounds if CL (#16888)

2026-07-06 13:53:58 -04:00

test_asm_gemm.py

llama: split current and next amax state (#16993)

2026-07-12 18:52:33 +09:00

test_const_folding.py

remove early THREEFRY const folding [PR] (#16850)

2026-07-03 15:00:35 -04:00

test_custom_kernel.py

remove dtypes base (#16931)

2026-07-08 11:48:11 -07:00

test_dtype_alu.py

skip modulo by zero in test_dtype_alu (#16404)

2026-05-27 17:09:05 -04:00

test_dtype.py

fix Tensor(np) dtype and support fp8 safetensor (#17019)

2026-07-14 09:31:21 -04:00

test_edgecases.py

Tensor.train -> TRAINING [PR] (#16705)

2026-06-22 15:13:22 -04:00

test_encodings.py

full removal of dtype.vec (#16996)

2026-07-12 09:25:50 -07:00

test_graph.py

remove copyin/copyout from Buffer (#17020)

2026-07-14 19:47:22 +03:00

test_interop.py

remove getenv(CI) (#16365)

2026-05-25 20:23:33 -04:00

test_isel.py

full removal of dtype.vec (#16996)

2026-07-12 09:25:50 -07:00

test_jit.py

many jit tests belong in unit (#16508)

2026-06-04 21:36:53 -04:00

test_linearizer_dumb.py

start dtypes.index [PR] (#16949)

2026-07-09 15:12:23 -04:00

test_linearizer.py

remove copyin/copyout from Buffer (#17020)

2026-07-14 19:47:22 +03:00

test_llama_kernels.py

llama: replace two stage amax with atomics (#17063)

2026-07-17 19:27:10 +09:00

test_multitensor.py

expect _offset support, CL and WEBGPU are outliers (#17014)

2026-07-13 18:53:32 -04:00

test_nn.py

Tensor.train -> TRAINING [PR] (#16705)

2026-06-22 15:13:22 -04:00

test_ops.py

use rusticl in ci (#16852)

2026-07-03 23:58:58 -04:00

test_opt_gemm.py

remove schedule() from tests batch 2 (#15923)

2026-04-25 10:44:41 +03:00

test_optim.py

more Tensor.training -> TRAINING [PR] (#16770)

2026-06-26 20:11:59 -04:00

test_pickle.py

test update for arange and eye (#16394)

2026-05-26 22:48:34 -04:00

test_profiler.py

remove copyin/copyout from Buffer (#17020)

2026-07-14 19:47:22 +03:00

test_quantize_onnx.py

remove Ops.DEVICE from Ops.PROGRAM [PR] (#16797)

2026-06-29 17:41:31 -04:00

test_randomness.py

remove Ops.DEVICE from Ops.PROGRAM [PR] (#16797)

2026-06-29 17:41:31 -04:00

test_rangeify.py

remove noop requires_grad_ calls (#16213)

2026-05-15 13:31:10 -04:00

test_renderer_failures.py

remove copyin/copyout from Buffer (#17020)

2026-07-14 19:47:22 +03:00

test_schedule.py

fix n^2 in limit_bufs by memoizing reachable loads [PR] (#17017)

2026-07-15 23:54:04 -07:00

test_setitem.py

limit CONST(UNIQUE) to invalids only (#16432)

2026-05-29 16:02:06 -04:00

test_softmax_fusion.py

make full with buffer=False deviceless (#16483)

2026-06-03 12:35:59 -04:00

test_stunning.py

Tensor.train -> TRAINING [PR] (#16705)

2026-06-22 15:13:22 -04:00

test_subbuffer.py

remove copyin/copyout from Buffer (#17020)

2026-07-14 19:47:22 +03:00

test_symbolic_jit.py

allocate generates a call (#14958)

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

test_symbolic_ops.py

Tensor.train -> TRAINING [PR] (#16705)

2026-06-22 15:13:22 -04:00

test_tensor_variable.py

explicit error for unbound Variable in program (#16971)

2026-07-10 16:23:59 -04:00

test_tensor.py

Tensor.train -> TRAINING [PR] (#16705)

2026-06-22 15:13:22 -04:00

test_to_numpy.py

move tests to test/backend (#14691)

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

test_transcendental.py

full removal of dtype.vec (#16996)

2026-07-12 09:25:50 -07:00

test_uops.py

remove copyin/copyout from Buffer (#17020)

2026-07-14 19:47:22 +03:00

test_zero_copy.py

move tests to test/backend (#14691)

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