deepcrayon
/
tinygrab
1
0
Fork 0
Code
tinygrab/test
History
chenyu ac183568be
llama JIT python runtime speedup (#1633) 
* no JIT call in TransformerBlock

* idea

* move 2 reshapes to jitted function

shrink inside jitted too, 6.3ms

remove back reshapes, 5.5ms

isinstance -> __class__ 4.99ms

* think

revert ops_gpu.py

revert symbolic.py too

PYOPENCL_COMPILER_OUTPUT=1

* cleanup

* fix cache shape for conversational model

only reshape if start_pos > 0

* small cleanup

* include var_vals.keys() to st.key

* add comments

* llama small update

* everything jitted again, similar structure to gpt2

* fix typing

* add TODO for in place update cache
 		2023-08-30 07:51:05 -07:00
..
external add cache collector (#1595) 2023-08-28 19:59:55 -07:00
extra move state to nn/state (#1619) 2023-08-22 07:36:24 -07:00
models llvm jitted (#1652) 2023-08-28 20:22:44 -07:00
unit move device to ops (#1646) 2023-08-23 08:30:17 -07:00
Dockerfile Docker fix (#1039) 2023-06-25 10:38:58 -07:00
__init__.py All devices are equal! (#196) 2020-12-15 23:44:08 -08:00
test_allocators.py move device to ops (#1646) 2023-08-23 08:30:17 -07:00
test_assign.py Limit dims based on max size (#1390) 2023-07-31 19:18:19 -07:00
test_cache_collector.py add cache collector (#1595) 2023-08-28 19:59:55 -07:00
test_conv.py Uast start (#1650) 2023-08-23 12:00:06 -07:00
test_conv_shapetracker.py add cache collector (#1595) 2023-08-28 19:59:55 -07:00
test_custom_function.py Optional: Reduce line count and simplify the LazyBuffer interface (#1642) 2023-08-22 21:01:10 -07:00
test_dtype.py move device to ops (#1646) 2023-08-23 08:30:17 -07:00
test_gc.py fix up eye and fix gc test 2023-02-27 06:53:18 -08:00
test_helpers.py add dtypes test (#1682) 2023-08-28 08:12:15 -07:00
test_jit.py support symbols in shrink (#1611) 2023-08-22 09:08:21 -07:00
test_lazybuffer.py add cache collector (#1595) 2023-08-28 19:59:55 -07:00
test_linearizer.py add cache collector (#1595) 2023-08-28 19:59:55 -07:00
test_net_speed.py CI < 5 minutes (#1252) 2023-07-23 13:00:56 -07:00
test_nn.py sparse cat cross entropy (#1597) 2023-08-21 14:14:54 -07:00
test_ops.py move device to ops (#1646) 2023-08-23 08:30:17 -07:00
test_optim.py Add WEBGPU tests to CI (#1463) 2023-08-06 10:32:01 -07:00
test_randomness.py Tensor.uniform with dtype=int bug fix (#1593) 2023-08-26 01:59:53 -04:00
test_specific_conv.py move device to ops (#1646) 2023-08-23 08:30:17 -07:00
test_speed_v_torch.py move device to ops (#1646) 2023-08-23 08:30:17 -07:00
test_symbolic_jit.py llama JIT python runtime speedup (#1633) 2023-08-30 07:51:05 -07:00
test_symbolic_ops.py fix symbolic_ops tests with Tensor.training=True (#1686) 2023-08-26 23:19:56 -04:00
test_symbolic_shapetracker.py support symbols in shrink (#1611) 2023-08-22 09:08:21 -07:00
test_tensor.py .cpu().numpy() -> .numpy() (#1594) 2023-08-21 09:53:29 -07:00
test_uops.py make TestNonFloatUOps.test_mul_bool pass on all platforms (#1557) 2023-08-16 11:34:09 -07:00
test_webgpu.js Revert "update editorconfig, enforce via CI (#1343)" (#1380) 2023-07-31 10:35:50 -07:00