George Hotz 9092f2a8c0 llm: add shared_expert and rope_dim support from qwen35 (#15673) ...

* llm: add shared_expert and rope_dim support from qwen35

* refactor into FFNBlock and TransformerBlock

* norms where they belong

2026-04-10 19:18:27 +08:00

..

__init__.py

more test cleanups (#2631)

2023-12-05 16:17:57 -08:00

test_allreduce.py

minimal mstack pr to fix allreduce (#10649)

2025-06-05 15:14:53 -07:00

test_assign.py

specify renderer in DEV, <dev>_<ren>=1 is deprecated (#15551)

2026-03-31 18:35:14 -04:00

test_attention.py

llm: add shared_expert and rope_dim support from qwen35 (#15673)

2026-04-10 19:18:27 +08:00

test_call.py

call always has tuple (#15297)

2026-03-17 10:58:46 +08:00

test_callify.py

Tensor.callify will be the JIT (#14983)

2026-02-24 18:42:24 +08:00

test_conv.py

update tests, WEBGPU=1 pytest . passes (#14089)

2026-01-10 00:03:02 -05:00

test_disk_tensor.py

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

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

test_dtype_spec.py

pass device into Tensor._frompy (#15385)

2026-03-20 05:09:01 -04:00

test_function.py

fix double after bug in rangeify (#15381)

2026-03-20 14:53:46 +08:00

test_getitem_ops.py

improve consecutive Tensor indexing (#14208)

2026-01-18 15:14:33 -05:00

test_gguf.py

Add Q5_0, Q5_1, and bfloat16 GGUF types (#15644)

2026-04-08 17:16:19 +08:00

test_gradient.py

remove gradient materialize_grads (#15367)

2026-03-19 23:36:03 -04:00

test_hashing.py

fix tests that failed locally on mac (#13872)

2025-12-29 11:23:38 -05:00

test_hcq_graph.py

jit: graphing in uops (#15489)

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

test_helpers.py

move more tests to test/null, split some existing ones (#14512)

2026-02-03 20:20:20 +08:00

test_indexing.py

differentiable setitem (#15054)

2026-02-27 17:25:15 -05:00

test_invalid_tensor.py

do not patch on invalid tensor tests (#15226)

2026-03-12 09:35:20 +08:00

test_linalg.py

add contiguous back to svd (#15074)

2026-02-28 16:49:26 -05:00

test_llm_moe.py

llm: add shared_expert and rope_dim support from qwen35 (#15673)

2026-04-10 19:18:27 +08:00

test_llm_server.py

llm: add shared_expert and rope_dim support from qwen35 (#15673)

2026-04-10 19:18:27 +08:00

test_masked_tensor.py

delete test_tensor_uop (#13951)

2026-01-01 09:25:05 -05:00

test_metal_graph.py

jit: graphing in uops (#15489)

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

test_realize_is_realize.py

jit case with Tensor.empty input, realized means allocated (#14930)

2026-02-21 16:33:55 +09:00

test_rearrange_einops.py

move more tests to test/null, split some existing ones (#14512)

2026-02-03 20:20:20 +08:00

test_schedule_cache.py

move more tests to test/null, split some existing ones (#14512)

2026-02-03 20:20:20 +08:00

test_setitem_schedule.py

assign into empty works (#15256)

2026-03-13 10:24:29 -04:00

test_shm_tensor.py

pass device into Tensor._frompy (#15385)

2026-03-20 05:09:01 -04:00

test_symbolic_tensor.py

move more tests to test/null, split some existing ones (#14512)

2026-02-03 20:20:20 +08:00

test_system_pci_scan_bus.py

system: fix pci_scan_bus vendor filter (#14885)

2026-02-19 17:23:32 +03:00

test_tar.py

accept filename decorator [pr] (#8049)

2024-12-05 11:40:59 +08:00

test_tensor_data.py

Tensor(uop) uses device from uop (#15340)

2026-03-18 02:56:06 -04:00

test_tensor_io.py

move more tests to test/null, split some existing ones (#14512)

2026-02-03 20:20:20 +08:00

test_tinyfs.py

fix tinyfs (#14974)

2026-02-24 08:50:53 -05:00

test_winograd.py

move more tests to test/null, split some existing ones (#14512)

2026-02-03 20:20:20 +08:00