TensorRT-LLMs/cpp/tensorrt_llm/kernels/decoderMaskedMultiheadAttention/cubin
Kaiyu Xie b777bd6475
Update TensorRT-LLM (#1725)
* Update TensorRT-LLM

---------

Co-authored-by: RunningLeon <mnsheng@yeah.net>
Co-authored-by: Tlntin <TlntinDeng01@Gmail.com>
Co-authored-by: ZHENG, Zhen <zhengzhen.z@qq.com>
Co-authored-by: Pham Van Ngoan <ngoanpham1196@gmail.com>
Co-authored-by: Nathan Price <nathan@abridge.com>
Co-authored-by: Tushar Goel <tushar.goel.ml@gmail.com>
Co-authored-by: Mati <132419219+matichon-vultureprime@users.noreply.github.com>
2024-06-04 20:26:32 +08:00
..
xqa_kernel_cubin.h Update TensorRT-LLM (#1725) 2024-06-04 20:26:32 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_16_sm_80.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_16_sm_86.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_32_sm_80.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_32_sm_86.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_0_m_16_sm_80.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_0_m_16_sm_86.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_0_m_32_sm_80.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_0_m_32_sm_86.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_16_sm_80.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_16_sm_86.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_32_sm_80.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_32_sm_86.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_0_m_16_sm_80.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_0_m_16_sm_86.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_0_m_16_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_0_m_16_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_0_m_32_sm_80.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_0_m_32_sm_86.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_0_m_32_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_0_m_32_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_80.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_86.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_89.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +08:00
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_90.cubin.cpp Update TensorRT-LLM (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1598) 2024-05-14 16:43:41 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +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 (#1455) 2024-04-16 19:40:08 +08:00