ghcr.io/huggingface/text-generation-inference:sha-52c6ddd-trtllm
ghcr.io
ghcr.iolinux/amd64sha-52c6ddd-trtllm大小: 未知更新于 2026年4月14日
Text Generation Inference是部署和服务大型语言模型（LLMs）的工具包，支持主流开源LLM的高性能文本生成。 支持Llama、Falcon等主流开源LLM部署；多GPU张量并行（Tensor Parallelism）加速推理；连续批处理（Continuous batching）提升请求吞吐量；集成bitsandbytes、GPT-Q等多种量化技术；提供与OpenAI Chat Completion API兼容的消息接口。 基于Rust、Python和gRPC构建服务端，采用transformers模型架构，通过Flash Attention和Paged Attention优化推理性能，使用NCCL实现分布式通信，支持Open Telemetry分布式追踪和Prometheus指标监控。 适用于生产环境下的LLM服务部署，包括聊天应用、推理API服务、企业级大模型服务端点等场景，支持Nvidia、AMD等多硬件平台。
拉取命令
轩辕镜像通过轩辕镜像拉取
专属域名未获取到
请登录使用轩辕镜像享受快速拉取体验，支持国内访问优化，速度提升
🚀 国内优化⚡ 访问优化🔒 安全可靠
原始仓库从原始仓库拉取镜像
docker pull ghcr.io/huggingface/text-generation-inference:sha-52c6ddd-trtllm更多版本
ghcr.io/huggingface/text-generation-inference:sha-24ee40d
sha-24ee40dghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:3.3.7
3.3.7ghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-efb94e0-intel-cpu
sha-efb94e0-intel-cpughcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-efb94e0
sha-efb94e0ghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-3498847
sha-3498847ghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:3.3.6-trtllm
3.3.6-trtllmghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:latest-rocm
latest-rocmghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-5e747f4
sha-5e747f4ghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:latest
latestghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-85790a1-intel-cpu
sha-85790a1-intel-cpughcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-db931fc-intel-cpu
sha-db931fc-intel-cpughcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-db931fc-trtllm
sha-db931fc-trtllmghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-24ee40d-intel-cpu
sha-24ee40d-intel-cpughcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:3.3.7-intel-cpu
3.3.7-intel-cpughcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-efb94e0-rocm
sha-efb94e0-rocmghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:3.3.7-trtllm
3.3.7-trtllmghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:3.3.7-intel-xpu
3.3.7-intel-xpughcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:3.3.7-gaudi
3.3.7-gaudighcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-24ee40d-trtllm
sha-24ee40d-trtllmghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-5e747f4-intel-cpu
sha-5e747f4-intel-cpughcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-db931fc-gaudi
sha-db931fc-gaudighcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-efb94e0-intel-xpu
sha-efb94e0-intel-xpughcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-efb94e0-neuron
sha-efb94e0-neuronghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-b4adbf2-intel-cpu
sha-b4adbf2-intel-cpughcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-db931fc-intel-xpu
sha-db931fc-intel-xpughcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-85790a1-neuron
sha-85790a1-neuronghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-55f7f7c
sha-55f7f7cghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-efb94e0-gaudi
sha-efb94e0-gaudighcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-b4adbf2-intel-xpu
sha-b4adbf2-intel-xpughcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-52c6ddd
sha-52c6dddghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-1b90c50
sha-1b90c50ghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-24ee40d-intel-xpu
sha-24ee40d-intel-xpughcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-24ee40d-gaudi
sha-24ee40d-gaudighcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-1b90c50-neuron
sha-1b90c50-neuronghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-5e747f4-rocm
sha-5e747f4-rocmghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-5e747f4-neuron
sha-5e747f4-neuronghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-b4adbf2-gaudi
sha-b4adbf2-gaudighcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-55f7f7c-trtllm
sha-55f7f7c-trtllmghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-3498847-gaudi
sha-3498847-gaudighcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-85790a1-intel-xpu
sha-85790a1-intel-xpughcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-85790a1-gaudi
sha-85790a1-gaudighcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-85790a1-trtllm
sha-85790a1-trtllmghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-1b90c50-intel-cpu
sha-1b90c50-intel-cpughcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-5e747f4-intel-xpu
sha-5e747f4-intel-xpughcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-52c6ddd-gaudi
sha-52c6ddd-gaudighcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-55f7f7c-gaudi
sha-55f7f7c-gaudighcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-5e747f4-gaudi
sha-5e747f4-gaudighcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-1b90c50-intel-xpu
sha-1b90c50-intel-xpughcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:sha-1b90c50-rocm
sha-1b90c50-rocmghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:latest-intel-cpu
latest-intel-cpughcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:latest-trtllm
latest-trtllmghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:latest-neuron
latest-neuronghcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:latest-gaudi
latest-gaudighcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:latest-intel-xpu
latest-intel-xpughcr.iolinux/amd64
ghcr.io/huggingface/text-generation-inference:2.4.0
2.4.0ghcr.iolinux/amd6414.11GB
ghcr.io/huggingface/text-generation-inference:2.1.1
2.1.1ghcr.iolinux/amd6410.66GB
ghcr.io/huggingface/text-generation-inference:sha-f08b44a-intel-cpu
sha-f08b44a-intel-cpughcr.iolinux/amd646.78GB
ghcr.io/huggingface/text-generation-inference:2.3.0
2.3.0ghcr.iolinux/amd6413.75GB
ghcr.io/huggingface/text-generation-inference:3.2.1
3.2.1ghcr.iolinux/amd6416.22GB
ghcr.io/huggingface/text-generation-inference:3.1.0
3.1.0ghcr.iolinux/amd6412.24GB
ghcr.io/huggingface/text-generation-inference:3.1.1
3.1.1ghcr.iolinux/amd6416.21GB
ghcr.io/huggingface/text-generation-inference:2.2
2.2ghcr.iolinux/amd6411.37GB
轩辕镜像配置手册
探索更多轩辕镜像的使用方法，找到最适合您系统的配置方式
Docker 配置
登录仓库拉取
通过 Docker 登录认证访问私有仓库
专属域名拉取
无需登录使用专属域名
K8s Containerd
Kubernetes 集群配置 Containerd
K3s
K3s 轻量级 Kubernetes 镜像加速
Dev Containers
VS Code Dev Containers 配置
Podman
Podman 容器引擎配置
Singularity/Apptainer
HPC 科学计算容器配置
其他仓库配置
ghcr、Quay、nvcr 等镜像仓库
Harbor 镜像源配置
Harbor Proxy Repository 对接专属域名
Portainer 镜像源配置
Portainer Registries 加速拉取
Nexus 镜像源配置
Nexus3 Docker Proxy 内网缓存
系统配置
需要其他帮助？请查看我们的 常见问题Docker 镜像访问常见问题解答 或 提交工单
镜像拉取常见问题
使用与功能问题
错误码与失败问题
docker pull 提示 manifest unknown 怎么办？
manifest unknown
docker pull 提示 no matching manifest 怎么办？
no matching manifest（架构）
镜像已拉取完成，却提示 invalid tar header 或 failed to register layer 怎么办？
invalid tar header（解压）
Docker pull 时 HTTPS / TLS 证书验证失败怎么办？
TLS 证书失败
Docker pull 时 DNS 解析超时或连不上仓库怎么办？
DNS 超时
Docker 拉取出现 410 Gone 怎么办？
410 Gone 排查
出现 402 或「流量用尽」提示怎么办？
402 与流量用尽
Docker 拉取提示 UNAUTHORIZED（401）怎么办？
401 认证失败
遇到 429 Too Many Requests（请求太频繁）怎么办？
429 限流
docker login 提示 Cannot autolaunch D-Bus，还算登录成功吗？
D-Bus 凭证提示
为什么会出现「单层超过 20GB」或 413，无法加速拉取？
413 与超大单层
账号 / 计费 / 权限
用户好评
来自真实用户的反馈，见证轩辕镜像的优质服务
oldzhang
运维工程师
Linux服务器
5
"Docker访问体验非常流畅，大镜像也能快速完成下载。"