Initial commit

0fc1daac · luopl · 0fc1daac · 0fc1daac · 0fc1daac · 0fc1daac
Commit 0fc1daac authored Jul 04, 2025 by luopl
20 changed files
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H200.json
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H200.json
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X.json
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X.json
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=AMD_Radeon_Graphics.json
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=AMD_Radeon_Graphics.json
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H200.json
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H200.json
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/README
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/configs/README
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/fused_moe.py
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/fused_moe.py
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/layer.py
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/fused_moe_triton/layer.py
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/router.py
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/router.py
--- a/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/topk.py
+++ b/sglang-v0.4.6.post5.dev/python/sglang/srt/layers/moe/topk.py