EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[CI] Fix lint CI (#5880)

Browse Source 
Quick fix for lint CI

- vLLM version: v0.13.0
- vLLM main:
bde38c11df

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2026-01-14 11:23:38 +08:00
committed by GitHub
parent e20813f441
commit e5c46bf169
1 changed files with 2 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/quantization/llm-compressor/w8a8_int8_dynamic_moe.py
View File

@@ -1,14 +1,11 @@
import torch import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor import oneshot from llmcompressor import oneshot
from llmcompressor.modifiers.quantization import QuantizationModifier from llmcompressor.modifiers.quantization import QuantizationModifier
from transformers import AutoModelForCausalLM, AutoTokenizer
MODEL_ID = "Qwen/Qwen3-30B-A3B-Instruct-2507" MODEL_ID = "Qwen/Qwen3-30B-A3B-Instruct-2507"
model = AutoModelForCausalLM.from_pretrained( model = AutoModelForCausalLM.from_pretrained(MODEL_ID, dtype=torch.bfloat16, trust_remote_code=True)
MODEL_ID, dtype=torch.bfloat16, trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID) tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
recipe = QuantizationModifier( recipe = QuantizationModifier(