George Hotz f7d4638e05 start LLM app, tons of clean up required. target is 200 line ollama (#11068) ...

* start LLM app, tons of clean up required. target is 200 line ollama

* kind of works

* simpler

* add k/v cache

* with SYM=1, it loops

* no rope cache

* simpler

* more cleanups

* cleanups

* works

* argparse and comments

* from gguf

* generate is a function

* no copy from cpu

* fix max context pass in

* test

* improve test

* ai2_arc

* fix 8B, use less ram

* 136 lines

2025-07-07 17:09:46 -07:00

..

external

start LLM app, tons of clean up required. target is 200 line ollama (#11068)

2025-07-07 17:09:46 -07:00

mockgpu

Very basic mock sqtt (#10512)

2025-05-26 14:38:28 -07:00

models

clean up binary_crossentropy_logits (#10958)

2025-06-24 12:23:40 -04:00

testextra

fix: skip kernel timing tests on ci cuda (#10348)

2025-05-16 11:48:06 -07:00

unit

Fix division by zero and mask bug in add views (#11088)

2025-07-07 10:05:47 -07:00

web

time viz (#10763)

2025-06-17 19:39:34 +03:00

__init__.py

All devices are equal! (#196)

2020-12-15 23:44:08 -08:00

Dockerfile

new cloud is cloudy [pr] (#7631)

2024-11-11 20:18:04 +08:00

helpers.py

remove unused test helper (#10999)

2025-06-27 13:48:48 +03:00

test_amd_llvm.py

llvm diagnostic error (#10267)

2025-05-16 02:03:20 -04:00

test_arange.py

move kernel to opt (#10899)

2025-06-20 15:22:28 -07:00

test_assign.py

rename lazydata to uop (#10698)

2025-06-08 08:42:22 -07:00

test_compile_failures.py

enable a few tests that work now (#7721)

2024-11-15 14:30:52 -05:00

test_const_folding.py

rename lazydata to uop (#10698)

2025-06-08 08:42:22 -07:00

test_copy_speed.py

CLANG -> CPU (#9189)

2025-02-20 18:03:09 -05:00

test_device_speed.py

add name uop (#9149)

2025-02-18 15:26:58 +08:00

test_dtype_alu.py

suppress filter_too_much on test_float_cast_to_unsigned (#10733)

2025-06-09 18:30:04 -04:00

test_dtype.py

fix view add 0 (#10840)

2025-06-16 16:46:12 -07:00

test_edgecases.py

fix tensor int floor div (#10327)

2025-05-21 06:46:54 -04:00

test_fusion_op.py

just schedule in test_recursive_pad [pr] (#8860)

2025-02-02 15:01:24 +02:00

test_gc.py

s/lb_refcount/uop_refcount [pr] (#10865)

2025-06-18 21:48:04 +03:00

test_graph.py

rename lazydata to uop (#10698)

2025-06-08 08:42:22 -07:00

test_hcq_iface.py

usb: cache writes into 0xa000 (#10191)

2025-05-07 16:03:35 +03:00

test_hcq.py

move kernel to opt (#10899)

2025-06-20 15:22:28 -07:00

test_image_dtype.py

rename lazydata to uop (#10698)

2025-06-08 08:42:22 -07:00

test_interop.py

hotfix: interop example (#9237)

2025-02-25 10:32:00 +03:00

test_jit_cases.py

enumerate cases of Tensors in the JIT (#10548)

2025-05-28 11:51:27 -07:00

test_jit.py

Cloud graph (#9876)

2025-05-07 11:41:41 -07:00

test_kernel_cache.py

CLANG -> CPU (#9189)

2025-02-20 18:03:09 -05:00

test_linalg.py

[bounty] Singular Value Decomposition (#10875)

2025-07-02 09:06:03 -07:00

test_linearizer_dumb.py

move kernel to opt (#10899)

2025-06-20 15:22:28 -07:00

test_linearizer_overflows.py

move kernel to opt (#10899)

2025-06-20 15:22:28 -07:00

test_linearizer.py

remove TC=3 not porting this (#11045)

2025-06-30 15:12:49 -07:00

test_memory_planner.py

s/lb_refcount/uop_refcount [pr] (#10865)

2025-06-18 21:48:04 +03:00

test_metal.py

Use MTLCompiler directly (v2) (#7920)

2024-12-04 16:36:48 +08:00

test_method_cache.py

simple LoadOps.ASSIGN (#3745)

2024-03-14 20:44:34 -07:00

test_multitensor.py

viz: non blocking UOp tracing (#10913)

2025-06-23 19:59:28 +03:00

test_net_speed.py

hotfix: test_net_speed can't backward before realize

2024-12-19 20:32:59 -08:00

test_nn.py

move sparse_categorical_crossentropy to test_ops (#11083)

2025-07-03 21:40:54 -04:00

test_ocl.py

Fix GPT2 with OpenCL backend. (#6821)

2024-10-01 16:57:22 +08:00

test_ops.py

Tensor.diagonal (#11122)

2025-07-07 16:21:26 -04:00

test_opt_gemm.py

move kernel to opt (#10899)

2025-06-20 15:22:28 -07:00

test_optim.py

raise RuntimeError in schedule_step if not Tensor.training [pr] (#8834)

2025-01-31 12:03:04 -05:00

test_outerworld_range.py

outerworld range test [pr] (#11059)

2025-07-02 14:28:44 -07:00

test_pickle.py

rename lazydata to uop (#10698)

2025-06-08 08:42:22 -07:00

test_profiler.py

support capturing cpu_profile on error (#11078)

2025-07-04 11:53:12 +03:00

test_quantize_onnx.py

rename DEFINE_ACC -> DEFINE_REG (#11006)

2025-06-27 11:09:25 -07:00

test_randomness.py

smaller tests are faster tests [pr] (#10704)

2025-06-08 10:54:19 -07:00

test_remote.py

Remote multihost (#10598)

2025-06-16 13:18:56 -07:00

test_renderer_failures.py

rename lazydata to uop (#10698)

2025-06-08 08:42:22 -07:00

test_sample.py

enable more webgpu tests (#9502)

2025-03-18 23:03:54 -04:00

test_schedule.py

force reduce to be in axis order (#10837)

2025-06-24 13:00:16 -07:00

test_search.py

kernel.py no longer permutes reduce axis [pr] (#10968)

2025-06-26 17:44:58 -07:00

test_setitem.py

little setitem test (#11064)

2025-07-02 15:10:24 -07:00

test_softmax_fusion.py

non recursive top_down_rewrite (#10729)

2025-06-09 16:33:04 -07:00

test_specific_conv.py

Solve get_grouped_dims does not split issue (#9085)

2025-02-16 19:57:29 -05:00

test_speed_v_torch.py

lil work on llvm speed (#10157)

2025-05-04 16:37:26 -07:00

test_stunning.py

assert in test_indexing_two_bind instead of silent fail (#10099)

2025-04-29 20:23:25 +08:00

test_subbuffer.py

redundant code (#11014)

2025-06-29 09:06:10 -07:00

test_symbolic_jit.py

support variable shape none slice in getitem (#10724)

2025-06-09 11:53:02 -07:00

test_symbolic_ops.py

Support symbolic slice with no start [pr] (#10775)

2025-06-11 16:00:38 -04:00

test_tensor_data.py

[BUGFIX] Tensor([]).data() (#7884)

2024-11-24 16:42:57 -05:00

test_tensor_uop.py

rename lazydata to uop (#10698)

2025-06-08 08:42:22 -07:00

test_tensor_variable.py

[bounty] [pr] index validation with z3 (#9981)

2025-04-24 08:06:08 -04:00

test_tensor.py

rename lazydata to uop (#10698)

2025-06-08 08:42:22 -07:00

test_tiny.py

hotfix: corealize in the tiny mnist test

2025-06-23 17:41:16 -07:00

test_to_numpy.py

Apply ruff linting rules to tests (#2473)

2023-11-27 21:24:06 -08:00

test_transcendental.py

Fix DSP transcendentals (#9542)

2025-03-22 11:08:18 +08:00

test_uop_graph.py

Perform index validation on load/store, not on the index (#10849)

2025-06-23 16:25:05 -07:00

test_uops_stats.py

move kernel to opt (#10899)

2025-06-20 15:22:28 -07:00

test_uops.py

cleanup: remove disabled TestIndexingOrdering (#11101)

2025-07-05 18:14:37 +03:00

test_winograd.py

remove some linearize calls from tests [pr] (#10978)

2025-06-25 12:37:17 -07:00

test_zero_copy.py

rename lazydata to uop (#10698)

2025-06-08 08:42:22 -07:00