TensorRT-LLMs/cpp/tensorrt_llm/kernels/decoderMaskedMultiheadAttention/cubin
Kaiyu Xie e06f537e08
Update TensorRT-LLM (#1019)
* Update TensorRT-LLM

---------

Co-authored-by: erenup <ping.nie@pku.edu.cn>
Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
2024-01-31 21:55:32 +08:00
..
xqa_kernel_cubin.h Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_16_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_16_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_32_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_32_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_64_nqpkv_0_m_16_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_64_nqpkv_0_m_16_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_64_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_64_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_64_nqpkv_0_m_32_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_64_nqpkv_0_m_32_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_64_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_64_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_128_nqpkv_0_m_16_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_128_nqpkv_0_m_16_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_128_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_128_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_128_nqpkv_0_m_32_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_128_nqpkv_0_m_32_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_128_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_128_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_0_m_16_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_0_m_16_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_0_m_32_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_0_m_32_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_0_m_16_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_0_m_16_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_0_m_32_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_0_m_32_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_0_m_16_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_0_m_16_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_0_m_32_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_0_m_32_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_bf16_pagedKV_64_nqpkv_1_m_1_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_bf16_pagedKV_64_nqpkv_1_m_1_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_bf16_pagedKV_64_nqpkv_1_m_1_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_bf16_pagedKV_64_nqpkv_1_m_1_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_bf16_pagedKV_128_nqpkv_1_m_1_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_bf16_pagedKV_128_nqpkv_1_m_1_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_bf16_pagedKV_128_nqpkv_1_m_1_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_bf16_pagedKV_128_nqpkv_1_m_1_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_e4m3_pagedKV_64_nqpkv_1_m_1_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_e4m3_pagedKV_64_nqpkv_1_m_1_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_e4m3_pagedKV_128_nqpkv_1_m_1_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_e4m3_pagedKV_128_nqpkv_1_m_1_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_int8_pagedKV_64_nqpkv_1_m_1_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_int8_pagedKV_64_nqpkv_1_m_1_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_int8_pagedKV_64_nqpkv_1_m_1_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_int8_pagedKV_64_nqpkv_1_m_1_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_int8_pagedKV_128_nqpkv_1_m_1_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_int8_pagedKV_128_nqpkv_1_m_1_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_int8_pagedKV_128_nqpkv_1_m_1_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_bf16_d_256_beam_4_kvt_int8_pagedKV_128_nqpkv_1_m_1_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_16_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_16_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_32_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_32_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_64_nqpkv_0_m_16_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_64_nqpkv_0_m_16_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_64_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_64_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_64_nqpkv_0_m_32_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_64_nqpkv_0_m_32_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_64_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_64_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_128_nqpkv_0_m_16_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_128_nqpkv_0_m_16_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_128_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_128_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_128_nqpkv_0_m_32_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_128_nqpkv_0_m_32_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_128_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_128_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_0_m_16_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_0_m_16_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_0_m_32_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_0_m_32_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_0_m_16_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_0_m_16_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_0_m_32_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_0_m_32_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_0_m_16_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_0_m_16_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_0_m_32_sm_80.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_0_m_32_sm_86.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#941) 2024-01-23 23:22:35 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_e4m3_pagedKV_64_nqpkv_1_m_1_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_e4m3_pagedKV_64_nqpkv_1_m_1_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_e4m3_pagedKV_128_nqpkv_1_m_1_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_e4m3_pagedKV_128_nqpkv_1_m_1_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_fp16_pagedKV_64_nqpkv_1_m_1_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_fp16_pagedKV_64_nqpkv_1_m_1_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_fp16_pagedKV_64_nqpkv_1_m_1_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_fp16_pagedKV_64_nqpkv_1_m_1_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_fp16_pagedKV_128_nqpkv_1_m_1_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_fp16_pagedKV_128_nqpkv_1_m_1_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_fp16_pagedKV_128_nqpkv_1_m_1_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_fp16_pagedKV_128_nqpkv_1_m_1_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_int8_pagedKV_64_nqpkv_1_m_1_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_int8_pagedKV_64_nqpkv_1_m_1_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_int8_pagedKV_64_nqpkv_1_m_1_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_int8_pagedKV_64_nqpkv_1_m_1_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_int8_pagedKV_128_nqpkv_1_m_1_sm_80.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_int8_pagedKV_128_nqpkv_1_m_1_sm_86.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_int8_pagedKV_128_nqpkv_1_m_1_sm_89.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00
xqa_kernel_dt_fp16_d_256_beam_4_kvt_int8_pagedKV_128_nqpkv_1_m_1_sm_90.cubin.cpp Update TensorRT-LLM (#1019) 2024-01-31 21:55:32 +08:00