Skip to content

add deepseek ep moe tune config #1431

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
valarLip merged 3 commits into from
Nov 19, 2025
Merged

add deepseek ep moe tune config #1431

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b0dec7d
add ptpc deepseek ep moe tuned config
junhaha666 Nov 18, 2025
e29b316
add block deepseek ep moe tune config
junhaha666 Nov 18, 2025
94838df
using 1stage moe for ptpc deepseek
junhaha666 Nov 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 14 additions & 0 deletions aiter/configs/tuned_fmoe.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -772,3 +772,17 @@ cu_num,token,model_dim,inter_dim,expert,topk,act_type,dtype,q_dtype_a,q_dtype_w,
80,256,7168,256,257,9,ActivationType.Silu,torch.bfloat16,torch.float8_e4m3fnuz,torch.float8_e4m3fnuz,QuantType.per_Token,1,0,32,0,536.7655,_ZN5aiter45fmoe_bf16_pertokenFp8_g1u1_vs_silu_1tg_32x256E,0.0%,0.0,Null,0.0%,536.7655,1,47.26,2646.03
80,512,7168,256,257,9,ActivationType.Silu,torch.bfloat16,torch.float8_e4m3fnuz,torch.float8_e4m3fnuz,QuantType.per_Token,1,0,32,0,560.4425,_ZN5aiter45fmoe_bf16_pertokenFp8_g1u1_vs_silu_1tg_32x256E,0.0%,0.0,Null,0.0%,560.4425,1,90.53,2544.06
80,1024,7168,256,257,9,ActivationType.Silu,torch.bfloat16,torch.float8_e4m3fnuz,torch.float8_e4m3fnuz,QuantType.per_Token,1,0,32,0,827.4898,_ZN5aiter45fmoe_bf16_pertokenFp8_g1u1_vs_silu_1tg_32x256E,0.0%,0.0,Null,0.0%,827.4898,1,122.62,1736.35
80,16,7168,2048,33,10,ActivationType.Silu,torch.bfloat16,torch.float8_e4m3fnuz,torch.float8_e4m3fnuz,QuantType.per_1x128,1,0,16,0,274.0603,_ZN5aiter59fmoe_stage1_bf16_pertokenFp8_blockscale_g1u1_16x256_2tg_pf3E,4.9%,150.3324,moe_ck2stages_gemm2_256x16x128x256_1x4_MulABScaleExpertWeightA8W8blkscale_v1_Nswizzle0_Quant4_MulRoutedWeight1_F8_F8_B16,0.3%,424.3927,0,33.21,3425.3
80,32,7168,2048,33,10,ActivationType.Silu,torch.bfloat16,torch.float8_e4m3fnuz,torch.float8_e4m3fnuz,QuantType.per_1x128,1,0,16,0,359.0112,moe_ck2stages_gemm1_256x16x128x256_1x4_MulABScaleExpertWeightA8W8blkscale_v1_Nswizzle0_Quant4_MulRoutedWeight0_silu_F8_F8_B16,0.0%,190.8827,moe_ck2stages_gemm2_256x16x128x256_1x4_MulABScaleExpertWeightA8W8blkscale_v1_Nswizzle0_Quant4_MulRoutedWeight1_F8_F8_B16,0.2%,549.8939,0,51.26,2644.17
Copy link
Collaborator

@valarLip valarLip Nov 19, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

no 2 stage solution should be here

80,64,7168,2048,33,10,ActivationType.Silu,torch.bfloat16,torch.float8_e4m3fnuz,torch.float8_e4m3fnuz,QuantType.per_1x128,1,0,32,0,631.2833,_ZN5aiter47fmoe_bf16_blockscaleFp8_g1u1_vs_silu_1tg_32x256E,0.9%,0.0,Null,0.0%,631.2833,1,89.3,2304.36
80,128,7168,2048,33,10,ActivationType.Silu,torch.bfloat16,torch.float8_e4m3fnuz,torch.float8_e4m3fnuz,QuantType.per_1x128,1,0,32,0,772.5524,_ZN5aiter47fmoe_bf16_blockscaleFp8_g1u1_vs_silu_1tg_32x256E,0.9%,0.0,Null,0.0%,772.5524,1,145.94,1884.76
80,256,7168,2048,33,10,ActivationType.Silu,torch.bfloat16,torch.float8_e4m3fnuz,torch.float8_e4m3fnuz,QuantType.per_1x128,1,0,32,0,1166.708,_ZN5aiter47fmoe_bf16_blockscaleFp8_g1u1_vs_silu_1tg_32x256E,0.9%,0.0,Null,0.0%,1166.708,1,193.27,1250.38
80,512,7168,2048,33,10,ActivationType.Silu,torch.bfloat16,torch.float8_e4m3fnuz,torch.float8_e4m3fnuz,QuantType.per_1x128,1,0,32,0,2209.3824,_ZN5aiter47fmoe_bf16_blockscaleFp8_g1u1_vs_silu_1tg_32x256E,0.8%,0.0,Null,0.0%,2209.3824,1,204.12,662.78
80,1024,7168,2048,33,10,ActivationType.Silu,torch.bfloat16,torch.float8_e4m3fnuz,torch.float8_e4m3fnuz,QuantType.per_1x128,1,0,32,0,4205.8762,_ZN5aiter50fmoe_bf16_blockscaleFp8_g1u1_vs_silu_1tg_ps_32x256E,0.9%,0.0,Null,0.0%,4205.8762,1,214.45,350.78
80,16,7168,2048,33,10,ActivationType.Silu,torch.bfloat16,torch.float8_e4m3fnuz,torch.float8_e4m3fnuz,QuantType.per_Token,1,0,32,0,442.3731,_ZN5aiter45fmoe_bf16_pertokenFp8_g1u1_vs_silu_1tg_32x256E,6.8%,0.0,Null,0.0%,442.3731,1,31.86,3286.07
80,32,7168,2048,33,10,ActivationType.Silu,torch.bfloat16,torch.float8_e4m3fnuz,torch.float8_e4m3fnuz,QuantType.per_Token,1,0,32,0,520.7061,_ZN5aiter45fmoe_bf16_pertokenFp8_g1u1_vs_silu_1tg_32x512E,5.4%,0.0,Null,0.0%,520.7061,1,54.13,2792.39
80,64,7168,2048,33,10,ActivationType.Silu,torch.bfloat16,torch.float8_e4m3fnuz,torch.float8_e4m3fnuz,QuantType.per_Token,1,0,32,0,622.6569,_ZN5aiter45fmoe_bf16_pertokenFp8_g1u1_vs_silu_1tg_32x256E,6.9%,0.0,Null,0.0%,622.6569,1,90.53,2336.28
80,128,7168,2048,33,10,ActivationType.Silu,torch.bfloat16,torch.float8_e4m3fnuz,torch.float8_e4m3fnuz,QuantType.per_Token,1,0,32,0,687.274,_ZN5aiter45fmoe_bf16_pertokenFp8_g1u1_vs_silu_1tg_32x512E,5.2%,0.0,Null,0.0%,687.274,1,164.04,2118.63
80,256,7168,2048,33,10,ActivationType.Silu,torch.bfloat16,torch.float8_e4m3fnuz,torch.float8_e4m3fnuz,QuantType.per_Token,1,0,32,0,1021.9423,_ZN5aiter45fmoe_bf16_pertokenFp8_g1u1_vs_silu_1tg_32x512E,5.4%,0.0,Null,0.0%,1021.9423,1,220.64,1427.51
80,512,7168,2048,33,10,ActivationType.Silu,torch.bfloat16,torch.float8_e4m3fnuz,torch.float8_e4m3fnuz,QuantType.per_Token,1,0,32,0,1749.1923,_ZN5aiter45fmoe_bf16_pertokenFp8_g1u1_vs_silu_1tg_32x512E,5.4%,0.0,Null,0.0%,1749.1923,1,257.82,837.15
80,1024,7168,2048,33,10,ActivationType.Silu,torch.bfloat16,torch.float8_e4m3fnuz,torch.float8_e4m3fnuz,QuantType.per_Token,1,0,32,0,3226.5114,_ZN5aiter45fmoe_bf16_pertokenFp8_g1u1_vs_silu_1tg_32x512E,5.3%,0.0,Null,0.0%,3226.5114,1,279.54,457.26
Loading