| .. |
|
__init__.py
|
[CI/Build] Move test_utils.py to tests/utils.py (#4425)
|
2024-05-13 23:50:09 +09:00 |
|
allclose_default.py
|
[ROCm] Fix some kernels failed unit tests (#2498)
|
2024-02-05 14:25:36 -08:00 |
|
conftest.py
|
[Kernel] Use flashinfer for decoding (#4353)
|
2024-05-03 15:51:27 -07:00 |
|
test_activation.py
|
[CI/Build] Move test_utils.py to tests/utils.py (#4425)
|
2024-05-13 23:50:09 +09:00 |
|
test_attention_selector.py
|
[Misc] Take user preference in attention selector (#4960)
|
2024-05-23 07:55:56 +09:00 |
|
test_attention.py
|
[Model] Support MAP-NEO model (#5081)
|
2024-05-30 19:24:41 -07:00 |
|
test_blocksparse_attention.py
|
[Kernel][Backend][Model] Blocksparse flash attention kernel and Phi-3-Small model (#4799)
|
2024-05-24 22:00:52 -07:00 |
|
test_cache.py
|
[Model] Support MAP-NEO model (#5081)
|
2024-05-30 19:24:41 -07:00 |
|
test_cutlass.py
|
[Kernel] Refactor CUTLASS kernels to always take scales that reside on the GPU (#5137)
|
2024-06-01 06:45:32 +00:00 |
|
test_flash_attn.py
|
[Kernel] Add flash-attn back (#4907)
|
2024-05-19 18:11:30 -07:00 |
|
test_int8_quant.py
|
[Kernel] Initial Activation Quantization Support (#4525)
|
2024-05-23 21:29:18 +00:00 |
|
test_layernorm.py
|
[Kernel] Layernorm performance optimization (#3662)
|
2024-03-30 14:26:38 -07:00 |
|
test_marlin_gemm.py
|
Marlin 24 prefill performance improvement (about 25% better on average) (#4983)
|
2024-05-23 02:39:27 -04:00 |
|
test_moe.py
|
[Kernel] Support MoE Fp8 Checkpoints for Mixtral (Static Weights with Dynamic/Static Activations) (#4527)
|
2024-05-04 11:45:16 -07:00 |
|
test_pos_encoding.py
|
[Model] Support MAP-NEO model (#5081)
|
2024-05-30 19:24:41 -07:00 |
|
test_prefix_prefill.py
|
[Bugfix][Kernel] allow non-power-of-2 for prefix prefill with alibi (#4573)
|
2024-05-08 09:19:58 -07:00 |
|
test_rand.py
|
[CI] Try introducing isort. (#3495)
|
2024-03-25 07:59:47 -07:00 |
|
test_sampler.py
|
[CI] Try introducing isort. (#3495)
|
2024-03-25 07:59:47 -07:00 |
