zhoulin/zl_bench
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Renew scripts

Browse Source
This commit is contained in:
Linz
2026-07-24 10:17:33 +00:00
parent c8a42b66ee
commit f98ec10fd0
3 changed files with 36 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -73,7 +73,7 @@ ttgir 关键设计：
```bash
# A 侧（基线编译器）：正常跑，自动 record autotune 选择
bash run_pytest.sh # -> runs/<op>_<ts_A>/
bash run_pytest.sh # -> runs/<op>_<ts_A>/
# B 侧（改动后编译器）：replay A 侧的 config，保证两侧同 config
REPLAY_FROM=$PWD/runs/<op>_<ts_A> bash run_pytest.sh
run_pytest.sh
+16 -21
View File
@@ -21,28 +21,23 @@ FLAGGEMS_DIR="${FLAGGEMS_DIR:-/workspace/FlagGems-dev}"
SHAPE_FILE="${SHAPE_FILE:-}"
read -r -d '' INLINE_YAML <<'YAML' || true
fused_marlin_moe_mxfp4:
# 4 个 MoE 模型 x 4 档 token 数（M=1,16,64,256）= 16 组 shape
shapes:
# Mixtral (E=8)
- [1, 8, 4096, 14336, 2]
- [16, 8, 4096, 14336, 2]
- [64, 8, 4096, 14336, 2]
- [256, 8, 4096, 14336, 2]
# DeepSeek-V3 (E=256, H=7168)
- [1, 256, 7168, 2048, 8]
- [16, 256, 7168, 2048, 8]
- [64, 256, 7168, 2048, 8]
- [256, 256, 7168, 2048, 8]
# Qwen3 (E=512)
- [1, 512, 4096, 1024, 10]
- [16, 512, 4096, 1024, 10]
- [64, 512, 4096, 1024, 10]
- [256, 512, 4096, 1024, 10]
# DeepSeek-V4-Flash (E=256, H=4096)
- [1, 256, 4096, 2048, 6]
- [16, 256, 4096, 2048, 6]
- [64, 256, 4096, 2048, 6]
- [256, 256, 4096, 2048, 6]
- [1, 256, 4096, 256, 6]
- [2, 256, 4096, 256, 6]
- [4, 256, 4096, 256, 6]
- [8, 256, 4096, 256, 6]
- [16, 256, 4096, 256, 6]
- [32, 256, 4096, 256, 6]
- [64, 256, 4096, 256, 6]
- [128, 256, 4096, 256, 6]
- [256, 256, 4096, 256, 6]
- [512, 256, 4096, 256, 6]
- [1024, 256, 4096, 256, 6]
- [2048, 256, 4096, 256, 6]
- [4096, 256, 4096, 256, 6]
- [8192, 256, 4096, 256, 6]
- [16384, 256, 4096, 256, 6]
- [32768, 256, 4096, 256, 6]
shape_desc: "num_tokens, num_experts, hidden_size, intermediate_size, topk"
YAML
shape/my_benchmark.yaml
+19
View File
@@ -0,0 +1,19 @@
fused_marlin_moe_mxfp4:
shapes:
- [1, 256, 4096, 256, 6]
- [2, 256, 4096, 256, 6]
- [4, 256, 4096, 256, 6]
- [8, 256, 4096, 256, 6]
- [16, 256, 4096, 256, 6]
- [32, 256, 4096, 256, 6]
- [64, 256, 4096, 256, 6]
- [128, 256, 4096, 256, 6]
- [256, 256, 4096, 256, 6]
- [512, 256, 4096, 256, 6]
- [1024, 256, 4096, 256, 6]
- [2048, 256, 4096, 256, 6]
- [4096, 256, 4096, 256, 6]
- [8192, 256, 4096, 256, 6]
- [16384, 256, 4096, 256, 6]
- [32768, 256, 4096, 256, 6]
shape_desc: "num_tokens, num_experts, hidden_size, intermediate_size, topk"