ef6abf3dc7
Adds ALL files needed for Dockerfile build:
- qwen3_6_scripts/ (baseline patches + our optimizations)
- vllm/ (full vllm package)
- paged_attention_v2_pytorch.py (V2 with single-bmm optimization)
- Dockerfile + computility-run.yaml
Our optimizations vs baseline:
1. paged_attn.py: pre-gathered context KV (eliminates 194 gather calls),
Triton try/fallback, V2 heuristic, threshold 32K→64K
2. paged_attention_v2_pytorch.py: fills NotImplementedError,
single-bmm Phase 1 (195 launches → 3)
3. patch_enable_triton.py: HAS_TRITON=True with safety fallback
4. patch_triton_tuning.py: BLOCK=64, NUM_WARPS=4 for BI-V100
5. computility-run.yaml: gpu-memory-utilization 0.9→0.95,
max-num-batched-tokens 8192→16384
This repo can now be submitted to dev.modelhub.org.cn as-is.
32 lines
811 B
Python
32 lines
811 B
Python
"""Utils for model executor."""
|
|
from typing import Any, Dict, Optional
|
|
|
|
import torch
|
|
|
|
from vllm.utils import seed_everything
|
|
|
|
|
|
def set_random_seed(seed: int) -> None:
|
|
seed_everything(seed)
|
|
|
|
|
|
def set_weight_attrs(
|
|
weight: torch.Tensor,
|
|
weight_attrs: Optional[Dict[str, Any]],
|
|
):
|
|
"""Set attributes on a weight tensor.
|
|
|
|
This method is used to set attributes on a weight tensor. This method
|
|
will not overwrite existing attributes.
|
|
|
|
Args:
|
|
weight: The weight tensor.
|
|
weight_attrs: A dictionary of attributes to set on the weight tensor.
|
|
"""
|
|
if weight_attrs is None:
|
|
return
|
|
for key, value in weight_attrs.items():
|
|
assert not hasattr(
|
|
weight, key), (f"Overwriting existing tensor attribute: {key}")
|
|
setattr(weight, key, value)
|