EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

refine fused_moe tuning docs (#5294)

Browse Source
This commit is contained in:
Xiaoyu Zhang
2025-04-13 01:01:13 +08:00
committed by GitHub
parent 690ec20587
commit 3e4794aad8
2 changed files with 11 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
benchmark/kernels/fused_moe_triton/README.md
View File

@@ -8,6 +8,11 @@ This directory contains benchmarking tools for MoE (Mixture of Experts) kernels.
Example usage:
```bash
# Tune Mixtral-8x7B with default settings
python benchmark/kernels/fused_moe_triton/tuning_fused_moe_triton.py \
--model mistralai/Mixtral-8x7B-Instruct-v0.1 \
--tune
# Tune Qwen2-57B with FP8 and TP=4
python benchmark/kernels/fused_moe_triton/tuning_fused_moe_triton.py \
--model Qwen/Qwen2-57B-A14B-Instruct \
@@ -15,9 +20,12 @@ python benchmark/kernels/fused_moe_triton/tuning_fused_moe_triton.py \
--dtype fp8_w8a8 \
--tune
# Tune Mixtral-8x7B with default settings
# Tune DeepSeek-V3 with FP8, TP=8 and n_share_experts_fusion=8
python benchmark/kernels/fused_moe_triton/tuning_fused_moe_triton.py \
--model mistralai/Mixtral-8x7B-Instruct-v0.1 \
--model deepseek-ai/DeepSeek-V3-0324 \
--tp-size 8 \
--n-share-experts-fusion 8 \
--dtype fp8_w8a8 \
--tune
```