Chunan Zeng 65c24c28f9 [Quant Kernel] refactored per token group quant fp8 to support int8 up-to 2x faster (#4396)

2025-03-23 23:44:17 -07:00

..

sgl_kernel_ops.h

[Quant Kernel] refactored per token group quant fp8 to support int8 up-to 2x faster (#4396)

2025-03-23 23:44:17 -07:00

trt_reduce_internal.cuh

fix custom allreduce performance/accuracy problem (#4477)

2025-03-16 12:16:30 -07:00

utils.h

Add moe topk softmax templated from vllm (#4302)

2025-03-14 12:03:33 -07:00