| .. |
|
__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 |
|
quant_utils.py
|
[Feature][Hardware][Amd] Add fp8 Linear Layer for Rocm (#7210)
|
2024-08-16 10:06:30 -07:00 |
|
test_activation.py
|
[Kernel][Misc] register ops to prevent graph breaks (#6917)
|
2024-09-11 12:52:19 -07:00 |
|
test_attention_selector.py
|
[Core] Subclass ModelRunner to support cross-attention & encoder sequences (towards eventual encoder/decoder model support) (#4942)
|
2024-08-06 16:51:47 -04:00 |
|
test_attention.py
|
[Kernel][Hardware][Amd]Custom paged attention kernel for rocm (#8310)
|
2024-09-13 17:01:11 -07:00 |
|
test_awq_triton.py
|
[Kernel] [Triton] [AMD] Adding Triton implementations awq_dequantize and awq_gemm to support AWQ (#7386)
|
2024-08-28 15:37:47 -04:00 |
|
test_blocksparse_attention.py
|
[Misc/Testing] Use torch.testing.assert_close (#7324)
|
2024-08-16 04:24:04 +00:00 |
|
test_cache.py
|
[Kernel][Misc] register ops to prevent graph breaks (#6917)
|
2024-09-11 12:52:19 -07:00 |
|
test_causal_conv1d.py
|
[Kernel/Model] Migrate mamba_ssm and causal_conv1d kernels to vLLM (#7651)
|
2024-08-28 15:06:52 -07:00 |
|
test_cutlass.py
|
[Kernel][Misc] register ops to prevent graph breaks (#6917)
|
2024-09-11 12:52:19 -07:00 |
|
test_encoder_decoder_attn.py
|
[Core] Subclass ModelRunner to support cross-attention & encoder sequences (towards eventual encoder/decoder model support) (#4942)
|
2024-08-06 16:51:47 -04:00 |
|
test_flash_attn.py
|
register custom op for flash attn and use from torch.ops (#7536)
|
2024-08-15 22:38:56 -07:00 |
|
test_flashinfer.py
|
[Core/Bugfix] Add query dtype as per FlashInfer API requirements. (#8173)
|
2024-09-05 05:12:26 +00:00 |
|
test_fp8_quant.py
|
[Feature][Hardware][Amd] Add fp8 Linear Layer for Rocm (#7210)
|
2024-08-16 10:06:30 -07:00 |
|
test_gguf.py
|
[Bugfix][Kernel] Add IQ1_M quantization implementation to GGUF kernel (#8357)
|
2024-09-15 16:51:44 -06:00 |
|
test_int8_quant.py
|
[Kernel] AQ AZP 3/4: Asymmetric quantization kernels (#7270)
|
2024-09-16 11:52:40 -07:00 |
|
test_layernorm.py
|
[Kernel][Misc] register ops to prevent graph breaks (#6917)
|
2024-09-11 12:52:19 -07:00 |
|
test_machete_gemm.py
|
[Kernel][Misc] register ops to prevent graph breaks (#6917)
|
2024-09-11 12:52:19 -07:00 |
|
test_mamba_ssm.py
|
[Kernel/Model] Migrate mamba_ssm and causal_conv1d kernels to vLLM (#7651)
|
2024-08-28 15:06:52 -07:00 |
|
test_marlin_gemm.py
|
[Kernel][Misc] register ops to prevent graph breaks (#6917)
|
2024-09-11 12:52:19 -07:00 |
|
test_moe.py
|
[Kernel] Enable 8-bit weights in Fused Marlin MoE (#8032)
|
2024-09-16 09:47:19 -06:00 |
|
test_pos_encoding.py
|
[Misc/Testing] Use torch.testing.assert_close (#7324)
|
2024-08-16 04:24:04 +00:00 |
|
test_prefix_prefill.py
|
[Core/Bugfix] Add FP8 K/V Scale and dtype conversion for prefix/prefill Triton Kernel (#7208)
|
2024-08-12 22:47:41 +00:00 |
|
utils.py
|
[CI/Build] Reorganize models tests (#7820)
|
2024-09-13 10:20:06 -07:00 |
