.. |
xqa_kernel_cubin.h
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_16_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_16_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_16_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_16_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_32_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_32_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_32_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_32_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_bf16_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_16_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_16_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_32_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_32_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_16_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_16_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_16_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_16_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_32_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_32_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_32_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_32_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_16_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_16_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_16_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_16_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_32_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_32_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_32_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_32_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_bf16_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_pagedKV_16_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_pagedKV_16_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_pagedKV_32_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_pagedKV_32_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_16_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_16_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_16_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_16_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_32_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_32_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_32_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_32_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_bf16_d_256_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_16_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_16_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_32_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_32_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_16_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_16_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_16_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_16_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_32_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_32_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_32_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_32_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_fp16_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_16_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_16_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_16_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_16_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_32_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_32_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_32_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_32_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_128_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_pagedKV_16_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_pagedKV_16_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_pagedKV_32_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_pagedKV_32_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_e4m3_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_16_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_16_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_16_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_16_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_32_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_32_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_32_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_32_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_fp16_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_128_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_16_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_16_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_16_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_16_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_32_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_32_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_32_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_32_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_80.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_86.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_89.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |
xqa_kernel_dt_fp16_d_256_beam_1_kvt_int8_pagedKV_64_nqpkv_8_m_8_sm_90.cubin.cpp
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
3 weeks ago |