GitLab

# Conflicts:
#	vllm/model_executor/models/deepseek_v2.py

# 第一个ip为D的第一个节点，第二个ip为D的第二个节点,配置:export IP_CONFIG_FILE=/data/xiabo/w4a8_1/ip_config.txt
192.168.1.1 192.168.1.100
192.168.1.2 192.168.1.101
192.168.1.3 192.168.1.102
10.16.1.75 10.16.1.76

修复pd分离开启异步发送时数据集推理时decode侧卡住问题

See merge request dcutoolkit/deeplearing/vllm!235

support prefix cache on kme
fix the error in test_moe caused by moe align not supporting 511 and 211
multi-modal switching to torch implementation on z100l&k100

# Conflicts:
#	vllm/model_executor/layers/fused_moe/ep_moe/layer.py

修复pd分离开启异步发送时decode侧判断条件卡住

See merge request dcutoolkit/deeplearing/vllm!233

修复awq 的mtp中的blockint8的问题

See merge request dcutoolkit/deeplearing/vllm!229

删除DPSK_FP16_QUICK，以及增加awq和blockwiseint8的shared_output接口

See merge request dcutoolkit/deeplearing/vllm!228

删除DPSK_FP16_QUICK，以及增加awq和blockwiseint8的shared_output接口

See merge request dcutoolkit/deeplearing/vllm!227

去掉all2all ep相关代码

See merge request dcutoolkit/deeplearing/vllm!226