add deepseek ep moe tune config #1431
Open
+14
−0
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
junhaha666
force-pushed
the
ds_ep_moe_tune_config
branch
from
406539e to
b0dec7d
Compare
Copilot finished reviewing on behalf of
junhaha666
November 18, 2025 13:08
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR adds 7 new tuned configuration entries for DeepSeek EP MOE (Mixture of Experts) to the performance tuning database.
- Adds configurations for varying token sizes (16, 32, 64, 128, 256, 512, 1024) for a specific DeepSeek EP MOE architecture
- New configurations use inter_dim=2048, expert=33, and topk=10, distinguishing them from previous entries
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
valarLip
reviewed
Nov 19, 2025
| 80,512,7168,2048,33,10,ActivationType.Silu,torch.bfloat16,torch.float8_e4m3fnuz,torch.float8_e4m3fnuz,QuantType.per_Token,1,0,64,0,865.1256,_ZN5aiter44fmoe_stage1_bf16_pertokenFp8_g1u1_64x256_pf3E,0.0%,755.7812,moe_ck2stages_gemm2_256x64x128x256_1x4_MulABScaleExpertWeight_v3_Nswizzle0_Quant2_MulRoutedWeight1_F8_F8_B16,0.0%,1620.9068,0,278.22,903.41 | ||
| 80,1024,7168,2048,33,10,ActivationType.Silu,torch.bfloat16,torch.float8_e4m3fnuz,torch.float8_e4m3fnuz,QuantType.per_Token,1,0,64,0,1623.3044,_ZN5aiter44fmoe_stage1_bf16_pertokenFp8_g1u1_64x256_pf3E,0.0%,1428.8629,moe_ck2stages_gemm2_256x64x128x128_1x4_MulABScaleExpertWeight_v3_Nswizzle0_Quant2_MulRoutedWeight1_F8_F8_B16,0.1%,3052.1673,0,295.51,483.38 | ||
| 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 |
Collaborator
There was a problem hiding this comment.
no 2 stage solution should be here
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Motivation
Technical Details
Test Plan
Test Result
Submission Checklist