Thomas Parnell 9a7e2d0534 [Bugfix] Allow vllm to still work if triton is not installed. (#6786) ...

Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>

2024-07-29 14:51:27 -07:00

..

__init__.py

…

allclose_default.py

…

conftest.py

…

quant_utils.py

[ Kernel ] FP8 Dynamic Per Token Quant - Add scale_ub (#6593)

2024-07-19 18:15:26 -07:00

test_activation.py

…

test_attention_selector.py

…

test_attention.py

[Model] H2O Danube3-4b (#6451)

2024-07-26 20:47:50 -07:00

test_blocksparse_attention.py

…

test_cache.py

[Model] H2O Danube3-4b (#6451)

2024-07-26 20:47:50 -07:00

test_cutlass.py

[Kernel] Tuned FP8 Kernels for Ada Lovelace (#6677)

2024-07-29 09:42:35 -06:00

test_encoder_decoder_attn.py

…

test_flash_attn.py

…

test_flashinfer.py

…

test_fp8_quant.py

[Bugfix][Kernel] Use int64_t for indices in fp8 quant kernels (#6649)

2024-07-22 14:08:30 -06:00

test_int8_quant.py

…

test_layernorm.py

…

test_marlin_gemm.py

[Kernel] Increase precision of GPTQ/AWQ Marlin kernel (#6795)

2024-07-27 17:52:33 -04:00

test_moe.py

…

test_pos_encoding.py

[Model] H2O Danube3-4b (#6451)

2024-07-26 20:47:50 -07:00

test_prefix_prefill.py

…

test_rand.py

…

test_sampler.py

[Bugfix] Allow vllm to still work if triton is not installed. (#6786)

2024-07-29 14:51:27 -07:00

utils.py

…