Update Triton configs for block fp8 kernels (#2641)

afa0341e · HandH1998 · GitHub · 30828e71 · afa0341e · afa0341e
Unverified Commit afa0341e authored Dec 29, 2024 by HandH1998 Committed by GitHub Dec 29, 2024
3 changed files
--- a/python/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
+++ b/python/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
--- a/python/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
+++ b/python/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
--- a/python/sglang/srt/layers/quantization/fp8_kernel.py
+++ b/python/sglang/srt/layers/quantization/fp8_kernel.py