shell-nlp/gpt_server

Issues

• 资源监控

  #23 opened 2 months ago by aaadrain
  2

• 安装依赖时出现python版本匹配错误

  #22 opened 2 months ago by FuncyLec
  8

• [請教] response_format相關實現

  #17 opened 2 months ago by milk333445
  5

• glm4-9b模型在lmdeploy-turbo下推理文不对题

  #21 opened 2 months ago by echohsq
  2

• 已品鉴 很美味 但建议把各个引擎的参数暴露出来,如dtype等

  #19 opened 3 months ago by sph116
  2

• qwen2-vl系列模型兼容

  #14 opened 3 months ago by aaadrain
  2

• 部署minicpm-v-2.6模型推理报错

  #20 opened 3 months ago by sph116
  3

• docker容器运行Qwen2.5-7b报错:TextEncodeInput must be Union

  #15 opened 4 months ago by wzs1566
  11

• 【请教】大佬请教一下config.yaml

  #16 opened 4 months ago by taurusduan
  5

• 服务器集群管理

  #18 opened 3 months ago by aaadrain
  1

• 【求助】构建镜像出错

  #7 opened 4 months ago by taurusduan
  10

• 会不会考虑支持多模态模型

  #11 opened 4 months ago by ehlxr
  10

• 依赖好多

  #12 opened 6 months ago by pc-mysql
  2

• support vllm

  #2 opened a year ago by shell-nlp
  1

• support LMDeploy

  #1 opened 9 months ago by shell-nlp
  1

• http api 请求 reranker 模型报错

  #10 opened 7 months ago by ehlxr
  4

• 纯CPU无法启动

  #9 opened 6 months ago by firstjack
  2

• embedding/reranker加速推理

  #5 opened 6 months ago by shell-nlp
  0

• 推理后端及接口问题（支持 tools功能 ）

  #4 opened 7 months ago by 315930399
  6

• 加载Embedding模型时，指定使用CPU，但还是加载到GPU

  #8 opened 7 months ago by lkfs74
  2

• rerank模型能否支持 http://ip:8082/v1/rerank 调用？

  #6 opened 8 months ago by edisonzf2020
  3

• 在windows下执行异常

  #3 opened 9 months ago by firstjack
  14