Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
19 changes: 0 additions & 19 deletions tests/integration/defs/perf/pytorch_model_config.py
Original file line number Diff line number Diff line change
Expand Up @@ -93,7 +93,6 @@ def get_model_yaml_config(model_label: str,
'enable_padding': False
},
'moe_config': {
'backend': 'TRTLLM',
'max_num_tokens': 32768
},
'speculative_config': {
Expand Down Expand Up @@ -228,18 +227,6 @@ def get_model_yaml_config(model_label: str,
'enable_attention_dp': True,
}
},
# Qwen3 models with fp4 quantization on B200 with moe backend equal to TRTLLM
{
'patterns': [
'qwen3_235b_a22b_fp4-bench-pytorch-float4-maxbs:512-maxnt:2048-input_output_len:1000,2000-con:8-ep:8-gpus:8',
],
'config': {
'enable_attention_dp': False,
'moe_config': {
'backend': 'TRTLLM'
}
}
},
{
'patterns': [
'qwen3_4b-bench-pytorch-streaming-bfloat16-maxbs:4-kv_frac:0.6-input_output_len:500,100-reqs:200-con:4',
Expand Down Expand Up @@ -317,9 +304,6 @@ def get_model_yaml_config(model_label: str,
'enable_padding': True,
'max_batch_size': 720,
},
'moe_config': {
'backend': 'TRTLLM'
},
'stream_interval': 10,
'num_postprocess_workers': 4
}
Expand All @@ -336,9 +320,6 @@ def get_model_yaml_config(model_label: str,
'enable_padding': True,
'max_batch_size': 720,
},
'moe_config': {
'backend': 'TRTLLM'
},
'stream_interval': 10,
'num_postprocess_workers': 4
}
Expand Down
Empty file.
Loading