Skip to content

Zhimding/fix aot moe pad 0522 #3313

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

Open
coderfeli wants to merge 8 commits into
base: main
Choose a base branch
from
Open

Zhimding/fix aot moe pad 0522 #3313

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
853247e
Support MoE pad fields in GPT-OSS configs
zhiding512 May 22, 2026
6ec4f7a
fix config
zhiding512 May 22, 2026
722ac53
Fix MoE padded dimension test reference
coderfeli May 23, 2026
16bd0b4
Apply Black formatting to MoE pad test
coderfeli May 23, 2026
1ecdc23
Merge branch 'main' into zhimding/fix_aot_moe_pad_0522
coderfeli May 23, 2026
73a43d2
feat(moe): add bias dimension to 2stage config lookup
zhiding512 May 25, 2026
dd915e1
Merge branch 'zhimding/fix_aot_moe_pad_0522' of github.com:ROCm/aiter…
zhiding512 May 25, 2026
b27c4cf
fix(moe): propagate bias/pad columns through tuner and runtime cfg lo…
zhiding512 May 25, 2026
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
57 changes: 45 additions & 12 deletions aiter/aot/flydsl/moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,6 +71,34 @@ def _row_swiglu_limit(row: dict[str, str]) -> float:
return _parse_optional_float(row.get("swiglu_limit"), "swiglu_limit") or 0.0


def _row_optional_int(row: dict[str, str], name: str) -> int:
value = row.get(name)
if value is None:
return 0
value = str(value).strip()
if value == "":
return 0
try:
return int(value)
except ValueError as e:
raise ValueError(f"{name} must be an int, got {value!r}") from e


def _row_optional_bool(row: dict[str, str], name: str) -> bool | None:
value = row.get(name)
if value is None:
return None
value = str(value).strip()
if value == "":
return None
value_lower = value.lower()
if value_lower in ("1", "true", "t", "yes", "y"):
return True
if value_lower in ("0", "false", "f", "no", "n"):
return False
raise ValueError(f"{name} must be a bool, got {value!r}")


def parse_csv(csv_path: str):
"""Parse the CSV and return a list of unique compile jobs.

Expand All @@ -93,6 +121,8 @@ def parse_csv(csv_path: str):
experts = int(row["expert"])
topk = int(row["topk"])
doweight_stage1 = bool(int(row.get("doweight_stage1", "0")))
hidden_pad = _row_optional_int(row, "hidden_pad")
intermediate_pad = _row_optional_int(row, "intermediate_pad")
cu_num = int(row.get("cu_num", "0"))
block_m = int(row.get("block_m", "0") or "0")
act_type = row.get("act_type", "")
Expand All @@ -101,19 +131,8 @@ def parse_csv(csv_path: str):
if act_type.strip().split(".")[-1].lower() == "swiglu"
else "silu"
)
q_type = row.get("q_type", "")
dtype = row.get("dtype", "")
q_dtype_w = row.get("q_dtype_w", "")
swiglu_limit = _row_swiglu_limit(row)
# Cover both runtime bias choices for fp4-weight MoE. Model configs
# share kernel families, and runtime bias selection can vary by
# activation dtype/model semantics.
bias_supported = (
q_type.strip().split(".")[-1] == "per_1x32"
and dtype in ("torch.bfloat16", "torch.float16")
and "float4_e2m1fn_x2" in q_dtype_w
)
enable_bias_options = [False, True] if bias_supported else [False]
enable_bias_options = [bool(_row_optional_bool(row, "bias"))]

# Detect stage1's fuse_quant from kernel suffix to align stage2's
# a2_scale shape with what runtime actually passes.
Expand Down Expand Up @@ -143,6 +162,8 @@ def parse_csv(csv_path: str):
"experts": experts,
"topk": topk,
"doweight_stage1": doweight_stage1,
"hidden_pad": hidden_pad,
"intermediate_pad": intermediate_pad,
"cu_num": cu_num,
"act": act,
"enable_bias": enable_bias,
Expand Down Expand Up @@ -200,6 +221,8 @@ def _precompile_to_cache(
enable_bias: bool = False,
stage1_fuse_quant=None,
swiglu_limit: float = 0.0,
hidden_pad: int = 0,
intermediate_pad: int = 0,
**kwargs,
):
"""Trigger MLIR compilation by calling the runtime stage1/stage2 entry points
Expand Down Expand Up @@ -554,6 +577,8 @@ def _make_a_user(a_dtype_user_shape):
a_scale_one=a_scale_one,
xcd_swizzle=xcd_swizzle,
swiglu_limit=swiglu_limit,
model_dim_pad=hidden_pad,
inter_dim_pad=intermediate_pad,
)
_run_compiled(exe, args)

Expand Down Expand Up @@ -723,6 +748,8 @@ def _make_a_user(a_dtype_user_shape):
b_nt=b_nt,
xcd_swizzle=xcd_swizzle,
enable_bias=enable_bias,
model_dim_pad=hidden_pad,
inter_dim_pad=intermediate_pad,
)
_run_compiled(exe, args)

Expand All @@ -734,6 +761,8 @@ def compile_one_config(
experts: int,
topk: int,
cu_num: int = 0,
hidden_pad: int = 0,
intermediate_pad: int = 0,
**kwargs,
) -> dict:
"""Compile one MoE kernel configuration and save to cache.
Expand All @@ -747,6 +776,8 @@ def compile_one_config(
shape_str = (
f"{kernel_name} "
f"model_dim={model_dim} inter_dim={inter_dim} "
f"hidden_pad={hidden_pad} "
f"intermediate_pad={intermediate_pad} "
f"E={experts} topk={topk}"
)
result = {
Expand All @@ -769,6 +800,8 @@ def compile_one_config(
experts=experts,
topk=topk,
cu_num=cu_num,
hidden_pad=hidden_pad,
intermediate_pad=intermediate_pad,
**kwargs,
)
elapsed = time.time() - t0
Expand Down
50 changes: 25 additions & 25 deletions aiter/configs/model_configs/gptoss_fp4_tuned_fmoe.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,25 +1,25 @@
cu_num,token,model_dim,inter_dim,expert,topk,act_type,dtype,q_dtype_a,q_dtype_w,q_type,use_g1u1,doweight_stage1,block_m,ksplit,us1,kernelName1,err1,us2,kernelName2,err2,us,run_1stage,xbf16,tflops,bw,_tag
256,256,3072,3072,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,32,0,208.4462,flydsl_moe1_afp4_wfp4_bf16_t32x128x256_w2,0.0%,109.1431,flydsl_moe2_afp4_wfp4_bf16_t32x256x256_atomic_bnt2_persist,5.0%,317.5893,0,0,182.57,11418.01,
256,512,3072,3072,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,32,0,215.3665,flydsl_moe1_afp4_wfp4_bf16_t32x128x256_w2,0.0%,109.5792,flydsl_moe2_afp4_wfp4_bf16_t32x128x256_atomic_bnt2,5.1%,324.9457,0,0,356.87,11166.78,
256,1024,3072,3072,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,208.4256,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w3_fp4,0.8%,121.3742,flydsl_moe2_afp4_wfp4_bf16_t64x256x256_atomic_bnt2,5.1%,329.7998,0,0,703.24,11016.73,
256,2048,3072,3072,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,289.0776,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w3_bnt0,0.0%,151.789,flydsl_moe2_afp4_wfp4_bf16_t64x128x256_atomic,5.0%,440.8666,0,0,1052.15,8262.71,
256,4096,3072,3072,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,128,0,404.0325,flydsl_moe1_afp4_wfp4_bf16_t128x128x256_w2_bnt0,0.0%,210.7843,flydsl_moe2_afp4_wfp4_bf16_t128x128x256_atomic,5.1%,614.8168,0,0,1508.93,5955.64,
256,8192,3072,3072,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,128,0,1319.2527,flydsl_moe1_afp4_wfp4_bf16_t128x128x256_w4_bnt0,0.0%,637.455,flydsl_moe2_afp4_wfp4_bf16_t128x128x256_atomic,5.0%,1956.7077,0,0,948.24,1890.61,
256,16384,3072,3072,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,1739.6561,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w4_bnt0,0.0%,940.8593,flydsl_moe2_afp4_wfp4_bf16_t64x128x256_atomic,5.1%,2680.5154,0,0,1384.38,1408.26,
256,32768,3072,3072,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,1991.1671,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w4_bnt0,0.0%,2466.0812,flydsl_moe2_afp4_wfp4_bf16_t64x128x256_atomic,5.0%,4457.2483,0,0,1665.09,880.78,
256,256,3072,1536,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,32,0,98.4171,flydsl_moe1_afp4_wfp4_bf16_t32x128x256_w2_fp4,0.9%,61.0182,flydsl_moe2_afp4_wfp4_bf16_t32x256x256_reduce_bnt2_persist,2.0%,159.4353,0,0,181.84,11379.53,
256,512,3072,1536,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,32,0,102.0754,flydsl_moe1_afp4_wfp4_bf16_t32x128x256_w4_fp4,0.9%,65.2416,flydsl_moe2_afp4_wfp4_bf16_t32x256x256_reduce_bnt2_persist,2.0%,167.317,0,0,346.54,10857.58,
256,1024,3072,1536,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,108.8592,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w4_fp4,0.8%,71.2891,flydsl_moe2_afp4_wfp4_bf16_t64x256x256_reduce_bnt2,2.0%,180.1483,0,0,643.71,10110.43,
256,2048,3072,1536,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,149.6562,flydsl_moe1_afp4_wfp4_bf16_t64x64x256_w4_bnt0,0.0%,92.8451,flydsl_moe2_afp4_wfp4_bf16_t64x128x256_atomic,3.6%,242.5013,0,0,956.4,7549.71,
256,4096,3072,1536,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,128,0,229.8446,flydsl_moe1_afp4_wfp4_bf16_t128x128x256_w2_bnt0,0.0%,142.3561,flydsl_moe2_afp4_wfp4_bf16_t128x128x256_reduce,2.0%,372.2007,0,0,1246.25,4969.6,
256,8192,3072,1536,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,340.00350000000003,flydsl_moe1_afp4_wfp4_bf16_t64x64x256_w4_bnt0,0.0%,270.0618,flydsl_moe2_afp4_wfp4_bf16_t64x128x256_atomic_persist,3.6%,610.0653,0,0,1520.68,3093.83,
256,16384,3072,1536,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,128,0,597.4298,flydsl_moe1_afp4_wfp4_bf16_t128x128x256_w3_bnt0,0.0%,451.0174,flydsl_moe2_afp4_wfp4_bf16_t128x128x256_reduce,2.0%,1048.4472,0,0,1769.69,1872.23,
256,32768,3072,1536,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,128,0,1065.1228,flydsl_moe1_afp4_wfp4_bf16_t128x128x256_w3_bnt0,0.0%,844.3695,flydsl_moe2_afp4_wfp4_bf16_t128x128x256_reduce,2.0%,1909.4923,0,0,1943.37,1107.06,
256,256,3072,512,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,37.8528,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w3_fp4,0.8%,28.9955,flydsl_moe2_afp4_wfp4_bf16_t64x128x256_reduce_bnt2,0.6%,66.8483,0,0,144.56,9070.37,
256,512,3072,512,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,32,0,41.4756,flydsl_moe1_afp4_wfp4_bf16_t32x128x256_w2,0.0%,30.988,flydsl_moe2_afp4_wfp4_bf16_t32x128x256_reduce_bnt2_persist,0.6%,72.4636,0,0,266.72,8400.06,
256,1024,3072,512,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,44.1622,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w3,0.0%,37.4254,flydsl_moe2_afp4_wfp4_bf16_t64x128x256_reduce,0.6%,81.5876,0,0,473.78,7518.51,
256,2048,3072,512,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,59.0778,flydsl_moe1_afp4_wfp4_bf16_t64x64x256_w3_bnt0,0.0%,51.3745,flydsl_moe2_afp4_wfp4_bf16_t64x128x256_reduce,0.6%,110.4523,0,0,699.93,5639.12,
256,4096,3072,512,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,79.0359,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w2_bnt0_xcd4,0.0%,93.1675,flydsl_moe2_afp4_wfp4_bf16_t64x256x256_reduce,0.6%,172.2034,0,0,897.88,3726.57,
256,8192,3072,512,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,124.6681,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w2_bnt0,0.0%,160.8729,flydsl_moe2_afp4_wfp4_bf16_t64x128x256_reduce_persist,0.6%,285.541,0,0,1082.99,2379.61,
256,16384,3072,512,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,206.4827,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w4_bnt0_xcd4,0.0%,285.1907,flydsl_moe2_afp4_wfp4_bf16_t64x256x256_reduce_xcd4,0.6%,491.6734,0,0,1257.9,1535.52,
256,32768,3072,512,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,367.6363,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w2_bnt0_xcd4,0.0%,517.2156,flydsl_moe2_afp4_wfp4_bf16_t64x256x256_reduce_xcd4,0.6%,884.8519,0,0,1397.92,1023.87,
cu_num,token,model_dim,inter_dim,expert,topk,act_type,dtype,q_dtype_a,q_dtype_w,q_type,use_g1u1,doweight_stage1,block_m,ksplit,us1,kernelName1,err1,us2,kernelName2,err2,us,run_1stage,xbf16,bias,hidden_pad,intermediate_pad,tflops,bw,_tag
256,256,3072,3072,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,32,0,208.4462,flydsl_moe1_afp4_wfp4_bf16_t32x128x256_w2,0.0%,109.1431,flydsl_moe2_afp4_wfp4_bf16_t32x256x256_atomic_bnt2_persist,5.0%,317.5893,0,0,True,192,192,182.57,11418.01,
256,512,3072,3072,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,32,0,215.3665,flydsl_moe1_afp4_wfp4_bf16_t32x128x256_w2,0.0%,109.5792,flydsl_moe2_afp4_wfp4_bf16_t32x128x256_atomic_bnt2,5.1%,324.9457,0,0,True,192,192,356.87,11166.78,
256,1024,3072,3072,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,208.4256,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w3_fp4,0.8%,121.3742,flydsl_moe2_afp4_wfp4_bf16_t64x256x256_atomic_bnt2,5.1%,329.7998,0,0,True,192,192,703.24,11016.73,
256,2048,3072,3072,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,289.0776,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w3_bnt0,0.0%,151.789,flydsl_moe2_afp4_wfp4_bf16_t64x128x256_atomic,5.0%,440.8666,0,0,True,192,192,1052.15,8262.71,
256,4096,3072,3072,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,128,0,404.0325,flydsl_moe1_afp4_wfp4_bf16_t128x128x256_w2_bnt0,0.0%,210.7843,flydsl_moe2_afp4_wfp4_bf16_t128x128x256_atomic,5.1%,614.8168,0,0,True,192,192,1508.93,5955.64,
256,8192,3072,3072,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,128,0,1319.2527,flydsl_moe1_afp4_wfp4_bf16_t128x128x256_w4_bnt0,0.0%,637.455,flydsl_moe2_afp4_wfp4_bf16_t128x128x256_atomic,5.0%,1956.7077,0,0,True,192,192,948.24,1890.61,
256,16384,3072,3072,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,1739.6561,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w4_bnt0,0.0%,940.8593,flydsl_moe2_afp4_wfp4_bf16_t64x128x256_atomic,5.1%,2680.5154,0,0,True,192,192,1384.38,1408.26,
256,32768,3072,3072,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,1991.1671,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w4_bnt0,0.0%,2466.0812,flydsl_moe2_afp4_wfp4_bf16_t64x128x256_atomic,5.0%,4457.2483,0,0,True,192,192,1665.09,880.78,
256,256,3072,1536,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,32,0,98.4171,flydsl_moe1_afp4_wfp4_bf16_t32x128x256_w2_fp4,0.9%,61.0182,flydsl_moe2_afp4_wfp4_bf16_t32x256x256_reduce_bnt2_persist,2.0%,159.4353,0,0,True,192,96,181.84,11379.53,
256,512,3072,1536,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,32,0,102.0754,flydsl_moe1_afp4_wfp4_bf16_t32x128x256_w4_fp4,0.9%,65.2416,flydsl_moe2_afp4_wfp4_bf16_t32x256x256_reduce_bnt2_persist,2.0%,167.317,0,0,True,192,96,346.54,10857.58,
256,1024,3072,1536,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,108.8592,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w4_fp4,0.8%,71.2891,flydsl_moe2_afp4_wfp4_bf16_t64x256x256_reduce_bnt2,2.0%,180.1483,0,0,True,192,96,643.71,10110.43,
256,2048,3072,1536,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,149.6562,flydsl_moe1_afp4_wfp4_bf16_t64x64x256_w4_bnt0,0.0%,92.8451,flydsl_moe2_afp4_wfp4_bf16_t64x128x256_atomic,3.6%,242.5013,0,0,True,192,96,956.4,7549.71,
256,4096,3072,1536,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,128,0,229.8446,flydsl_moe1_afp4_wfp4_bf16_t128x128x256_w2_bnt0,0.0%,142.3561,flydsl_moe2_afp4_wfp4_bf16_t128x128x256_reduce,2.0%,372.2007,0,0,True,192,96,1246.25,4969.6,
256,8192,3072,1536,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,340.00350000000003,flydsl_moe1_afp4_wfp4_bf16_t64x64x256_w4_bnt0,0.0%,270.0618,flydsl_moe2_afp4_wfp4_bf16_t64x128x256_atomic_persist,3.6%,610.0653,0,0,True,192,96,1520.68,3093.83,
256,16384,3072,1536,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,128,0,597.4298,flydsl_moe1_afp4_wfp4_bf16_t128x128x256_w3_bnt0,0.0%,451.0174,flydsl_moe2_afp4_wfp4_bf16_t128x128x256_reduce,2.0%,1048.4472,0,0,True,192,96,1769.69,1872.23,
256,32768,3072,1536,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,128,0,1065.1228,flydsl_moe1_afp4_wfp4_bf16_t128x128x256_w3_bnt0,0.0%,844.3695,flydsl_moe2_afp4_wfp4_bf16_t128x128x256_reduce,2.0%,1909.4923,0,0,True,192,96,1943.37,1107.06,
256,256,3072,512,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,37.8528,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w3_fp4,0.8%,28.9955,flydsl_moe2_afp4_wfp4_bf16_t64x128x256_reduce_bnt2,0.6%,66.8483,0,0,True,192,152,144.56,9070.37,
256,512,3072,512,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,32,0,41.4756,flydsl_moe1_afp4_wfp4_bf16_t32x128x256_w2,0.0%,30.988,flydsl_moe2_afp4_wfp4_bf16_t32x128x256_reduce_bnt2_persist,0.6%,72.4636,0,0,True,192,152,266.72,8400.06,
256,1024,3072,512,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,44.1622,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w3,0.0%,37.4254,flydsl_moe2_afp4_wfp4_bf16_t64x128x256_reduce,0.6%,81.5876,0,0,True,192,152,473.78,7518.51,
256,2048,3072,512,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,59.0778,flydsl_moe1_afp4_wfp4_bf16_t64x64x256_w3_bnt0,0.0%,51.3745,flydsl_moe2_afp4_wfp4_bf16_t64x128x256_reduce,0.6%,110.4523,0,0,True,192,152,699.93,5639.12,
256,4096,3072,512,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,79.0359,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w2_bnt0_xcd4,0.0%,93.1675,flydsl_moe2_afp4_wfp4_bf16_t64x256x256_reduce,0.6%,172.2034,0,0,True,192,152,897.88,3726.57,
256,8192,3072,512,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,124.6681,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w2_bnt0,0.0%,160.8729,flydsl_moe2_afp4_wfp4_bf16_t64x128x256_reduce_persist,0.6%,285.541,0,0,True,192,152,1082.99,2379.61,
256,16384,3072,512,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,206.4827,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w4_bnt0_xcd4,0.0%,285.1907,flydsl_moe2_afp4_wfp4_bf16_t64x256x256_reduce_xcd4,0.6%,491.6734,0,0,True,192,152,1257.9,1535.52,
256,32768,3072,512,128,4,ActivationType.Swiglu,torch.bfloat16,torch.float4_e2m1fn_x2,torch.float4_e2m1fn_x2,QuantType.per_1x32,1,0,64,0,367.6363,flydsl_moe1_afp4_wfp4_bf16_t64x128x256_w2_bnt0_xcd4,0.0%,517.2156,flydsl_moe2_afp4_wfp4_bf16_t64x256x256_reduce_xcd4,0.6%,884.8519,0,0,True,192,152,1397.92,1023.87,
Loading
Loading