Robert Shaw 7c008c51a9

[ Misc ] Refactor MoE to isolate Fp8 From Mixtral (#5970) ...

Co-authored-by: Robert Shaw <rshaw@neuralmagic>
Co-authored-by: Michael Goin <michael@neuralmagic.com>

2024-07-02 21:54:35 +00:00

..

__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

[Misc] Add CustomOp interface for device portability (#5255)

2024-06-05 09:18:19 -07:00

test_attention_selector.py

[Hardware][Intel] OpenVINO vLLM backend (#5379)

2024-06-28 13:50:16 +00:00

test_attention.py

[mypy] Enable type checking for test directory (#5017)

2024-06-15 04:45:31 +00:00

test_blocksparse_attention.py

[mypy] Enable type checking for test directory (#5017)

2024-06-15 04:45:31 +00:00

test_cache.py

[mypy] Enable type checking for test directory (#5017)

2024-06-15 04:45:31 +00:00

test_cutlass.py

[misc][cuda] use nvml to avoid accidentally cuda initialization (#6007)

2024-06-30 20:07:34 -07:00

test_flash_attn.py

[mypy] Enable type checking for test directory (#5017)

2024-06-15 04:45:31 +00:00

test_int8_quant.py

[Kernel][Misc] Use TORCH_LIBRARY instead of PYBIND11_MODULE for custom ops (#5047)

2024-06-09 16:23:30 -04:00

test_layernorm.py

[Misc] Add CustomOp interface for device portability (#5255)

2024-06-05 09:18:19 -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

[ Misc ] Refactor MoE to isolate Fp8 From Mixtral (#5970)

2024-07-02 21:54:35 +00:00

test_pos_encoding.py

[mypy] Enable type checking for test directory (#5017)

2024-06-15 04:45:31 +00:00

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

utils.py

[Bugfix]: During testing, use pytest monkeypatch for safely overriding the env var that indicates the vLLM backend (#5210)

2024-06-03 20:32:57 -07:00