Byron Hsu b5caa22dfb [kernel] port rope cuda kernel to sgl-kernel (#2993) ...

Co-authored-by: Yineng Zhang <me@zhyncs.com>

2025-01-20 20:58:51 +08:00

..

test_int8_gemm.py

Update int8 gemm config (#2774)

2025-01-07 19:47:37 +08:00

test_moe_align.py

Sampling penalties memory interface (#2870)

2025-01-13 23:09:00 +08:00

test_rotary_embedding.py

[kernel] port rope cuda kernel to sgl-kernel (#2993)

2025-01-20 20:58:51 +08:00

test_sampling_scaling_penalties.py

add sampling_scaling_penalties kernel (#2846)

2025-01-12 19:38:17 -08:00

test_trt_reduce.py

optimize custom allreduce kernel (#2904)

2025-01-16 03:04:25 +08:00