| .. |
|
xqa_kernel_cubin.h
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_16_sm_80.cubin.cpp
|
Update TensorRT-LLM (#846)
|
2024-01-09 21:03:35 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_16_sm_86.cubin.cpp
|
Update TensorRT-LLM (#846)
|
2024-01-09 21:03:35 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_16_sm_89.cubin.cpp
|
Update TensorRT-LLM (#846)
|
2024-01-09 21:03:35 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_16_sm_90.cubin.cpp
|
Update TensorRT-LLM (#846)
|
2024-01-09 21:03:35 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_32_sm_80.cubin.cpp
|
Update TensorRT-LLM (#846)
|
2024-01-09 21:03:35 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_32_sm_86.cubin.cpp
|
Update TensorRT-LLM (#846)
|
2024-01-09 21:03:35 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_32_sm_89.cubin.cpp
|
Update TensorRT-LLM (#846)
|
2024-01-09 21:03:35 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_0_m_32_sm_90.cubin.cpp
|
Update TensorRT-LLM (#846)
|
2024-01-09 21:03:35 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_8_m_8_sm_80.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_8_m_8_sm_86.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_8_m_8_sm_89.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_8_m_8_sm_90.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_80.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_86.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_89.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_90.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_80.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_86.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_89.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_90.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_80.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_86.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_89.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_90.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_16_sm_80.cubin.cpp
|
Update TensorRT-LLM (#846)
|
2024-01-09 21:03:35 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_16_sm_86.cubin.cpp
|
Update TensorRT-LLM (#846)
|
2024-01-09 21:03:35 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_16_sm_89.cubin.cpp
|
Update TensorRT-LLM (#846)
|
2024-01-09 21:03:35 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_16_sm_90.cubin.cpp
|
Update TensorRT-LLM (#846)
|
2024-01-09 21:03:35 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_32_sm_80.cubin.cpp
|
Update TensorRT-LLM (#846)
|
2024-01-09 21:03:35 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_32_sm_86.cubin.cpp
|
Update TensorRT-LLM (#846)
|
2024-01-09 21:03:35 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_32_sm_89.cubin.cpp
|
Update TensorRT-LLM (#846)
|
2024-01-09 21:03:35 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_0_m_32_sm_90.cubin.cpp
|
Update TensorRT-LLM (#846)
|
2024-01-09 21:03:35 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_8_m_8_sm_80.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_8_m_8_sm_86.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_8_m_8_sm_89.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_8_m_8_sm_90.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (#846)
|
2024-01-09 21:03:35 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_80.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_86.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_89.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |
|
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_90.cubin.cpp
|
Update TensorRT-LLM (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +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 (20240116) (#891)
|
2024-01-16 20:03:11 +08:00 |