vllm/tests/kernels
Eric Xihui Lin 8e192ff967
[Kernel][Backend][Model] Blocksparse flash attention kernel and Phi-3-Small model (#4799)
Co-authored-by: beagleski <yunanzhang@microsoft.com>
Co-authored-by: bapatra <bapatra@microsoft.com>
Co-authored-by: Barun Patra <codedecde@users.noreply.github.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
2024-05-24 22:00:52 -07:00
..
__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 [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 [CI/Build] Move test_utils.py to tests/utils.py (#4425) 2024-05-13 23:50:09 +09:00
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 [Kernel] Refactor FP8 kv-cache with NVIDIA float8_e4m3 support (#4535) 2024-05-09 18:04:17 -06:00
test_cutlass.py [Kernel] Fixup for CUTLASS kernels in CUDA graphs (#4954) 2024-05-22 14:10:43 +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 [Bugfix] fix rope error when load models with different dtypes (#4835) 2024-05-17 18:43:34 +09:00
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