SGLang
Model-serving framework for running supported language and multimodal models on customer-controlled compute.
7 sources checked by an editor on · Product website ↗
Read this page as JSON or Markdown.
Deployment terms: BYOC · control plane · data plane · private offer
· Open requirements shortlist · Estimate operating costs
Compare this listing with another →
SGLang debug dumper code execution
CVE-2026-111391 identifies code execution in the debug dumper filter. Check the debug endpoint exposure and authentication boundary.
Scope: CVE record: SGLang 0.5.10–0.5.22. The open upstream report and reviewed v0.5.23 code do not establish a fixed release.
Requires dumper configuration access and a subsequent model execution reaching a dumper hook. In shared-API mode, an ordinary API key can suffice without a separate admin key; authentication configuration changes exposure.
Action: Disable or isolate debug dumper endpoints and verify an upstream fix before treating a newer release as remediated.
Primary source · Upstream report and authentication conditions · Reviewed v0.5.23 filter implementation · Reviewed 2026-11-16
What lands where
Supplied by
Vendor or project
Install the package or use official containers; the reviewed primary installation path targets Linux with supported NVIDIA GPUs and compatible drivers.
Runs in
Documented customer environment
Customer-operated inference server and model weights on configured accelerator hosts
- Google Cloud: Customer cloud account
- Google Cloud
Servers / containers
Operated by
Your team
Customer manages accelerator capacity, model artifacts, runtime compatibility, endpoint access, including isolation of debug and dumper routes, monitoring, and upgrades.
Deployment boundaries by provider
- Google Cloud: Customer cloud account · Customer-operated
Resources in the customer's cloud account, subscription, project or tenancy. Managed cloud services still have shared responsibilities.
SGLang compatibility with GKE Inference Gateway ↗ · Source checked 2026-11-12
Application operations and account ownership are separate from infrastructure operations. Confirm external services, telemetry, support access and backup destinations for the chosen path.
| Install method | Install the package or use official containers; the reviewed primary installation path targets Linux with supported NVIDIA GPUs and compatible drivers. |
|---|---|
| Infrastructure | Servers / containers Customer-operated inference server and model weights on configured accelerator hosts. This is a customer-operated server/container deployment; portability does not establish named cloud-provider support. |
| Licensing model | Open Source / Open Core Apache License 2.0 for upstream SGLang. Model weights and hardware/runtime dependencies have their own licenses. This classification covers the reviewed upstream edition; external services and dependencies retain their own terms. |
| License | Apache License 2.0 for upstream SGLang. Model weights and hardware/runtime dependencies have their own licenses. |
Buyer diligence
Answers apply to the reviewed edition and deployment. Expand a row for qualifications and sources.
How to read these facts
Not researched means no field-specific review is recorded. Not confirmed means sources were checked but did not establish an answer. Availability, eligibility and edition-dependent findings retain the scope given in their evidence. A vendor’s hosted-service certification does not automatically cover your deployment. Evidence coverage is not a feature score.
6 of 12 fields researched (50%) · 4 documented · 2 unresolved. Evidence coverage is not a feature score.
- Single sign-on
Not confirmedEvidence and scope for Single sign-on
Server arguments document inference and administrative API keys with separate endpoint rules. The reviewed upstream configuration does not establish SAML/OIDC login, user provisioning or a supported IdP integration. Confirm a gateway-based identity design instead of treating a static API key as SSO.
Upstream inference-server/API authentication; federation unresolved · Source ↗ · Reviewed 2026-11-20
Sources checked — unresolved · Editor reviewed.
- Security controls
DocumentedEvidence and scope for Security controls
The reported shared-API dumper exposure requires DUMPER_SERVER_PORT=reuse and access to configure a filter followed by a model execution. Without a separate admin key, an ordinary API key can reach the route; without any API key, it can be anonymous. A configured admin key is required when present. Keep dumper/debug routes disabled or network-isolated. The CVE enumerates 0.5.10–0.5.22; retained filter code in 0.5.23 is not by itself a complete assessment of every authentication configuration.
Debug dumper trust boundary and deployment precautions; not a blanket claim that all SGLang endpoints or all later releases are unauthenticated · Source ↗ · Primary CVE record ↗ · SGLang v0.5.23 shared dumper route and authentication level ↗ · SGLang v0.5.23 filter implementation ↗ · Reviewed 2026-11-16
Documented · Editor reviewed.
- Deployment artifact / IaC
DocumentedEvidence and scope for Deployment artifact / IaC
The upstream installation guide supplies container, Compose and Kubernetes options for model serving. Match model/backend, accelerator drivers and selected image; examples do not establish a universal GPU or memory minimum.
Upstream self-hosted deployment; not a provider support or production-readiness certification · Source ↗ · Reviewed 2026-11-14
Documented · Editor reviewed.
- Minimum footprint / sizing
Not confirmedEvidence and scope for Minimum footprint / sizing
The server configuration sizes model loading, quantization, parallelism, KV cache and admitted requests through memory controls such as mem-fraction-static. It does not establish one safe CPU/RAM/VRAM minimum. Select model, precision, context, concurrency and availability, then validate the chosen accelerator topology.
Model and serving-configuration dependent; complete production footprint unresolved · Source ↗ · Reviewed 2026-11-20
Sources checked — unresolved · Editor reviewed.
- License pricing
DocumentedEvidence and scope for License pricing
The reviewed upstream core is Apache-2.0 licensed. Optional services, bundled dependencies, commercial distributions and support can have separate terms. This records the source licence, not an infrastructure or operating-cost estimate. Model weights and external model APIs require their own review.
Upstream core licence; commercial features, support and hosting priced separately · Source ↗ · Reviewed 2026-11-20
Documented · Editor reviewed.
- Release snapshot / cadence
DocumentedEvidence and scope for Release snapshot / cadence
The publisher-designated GitHub release checked was v0.5.23, published 2026-11-02. This is a release snapshot, not a promised cadence, support designation or approval to substitute it into a provider package.
Upstream sgl-project/sglang release record; commercial editions and deployment packages may differ · Source ↗ · Reviewed 2026-11-14
Documented · Editor reviewed.
Show all fields (6 not researched)
- Marketplace delivery
- Not researched Supply a public source.
- Cloud commitment eligibility
- Not researched Supply a public source.
- SCIM provisioning
- Not researched Supply a public source.
- Compliance attestations
- Not researched Supply a public source.
- Air-gapped operation
- Not researched Supply a public source.
- Operating cost estimate
- Not researched Supply a public source.
Scope & considerations
Model downloads may require external registries and gated-model credentials. Pin compatible model/runtime/image versions and review model-specific permissions. Generic container instructions do not establish deployment badges for every hyperscaler. CVE-2026-111391 rates SGLang 0.5.10 through 0.5.22 critical (CVSS v4.0 9.2) for Python code execution through the debug dumper filter. The upstream report demonstrates the shared-API path with DUMPER_SERVER_PORT=reuse: an ordinary API-key holder can reach it when no separate admin API key is configured; access can be anonymous when no API key is configured. With an admin API key configured, that key is required. Exploitation also requires access to the dumper configuration and a subsequent model execution that reaches a dumper hook. Upstream issue #44188 remains open, and the v0.5.23 tag still contains the eval-based filter path even though that tag is outside the CVE record's enumerated affected range. Do not enable or expose the debug dumper endpoint; restrict it at the network layer and verify an upstream fix before treating a later version as remediated.
Community & maintenance
The upstream release history documents hundreds of pull requests from many named contributors and sustained releases; its README describes production use across labs, platforms and enterprises.
Category fit
- AI inference & gateways
- Model-serving framework for LLM and multimodal inference; an inference runtime rather than a full multi-provider governance gateway.
- AI tools & infrastructure
- Customer-operated inference infrastructure for serving supported model weights.
Compare within AI inference & gateways
- LiteLLM Proxy Self-HostedSelf-hosted AI API gateway providing model routing, access controls and usage tracking.
- AWS
- Azure
- Google Cloud
- Railway
- Render
- LocalAILocal model inference service exposing configurable AI capabilities through compatible API endpoints.
- AWS
- NVIDIA AI EnterpriseCommercial enterprise AI software suite deployed on customer cloud GPU instances or managed Kubernetes clusters.
- AWS
- Azure
- Google Cloud
- Oracle Cloud
- Alibaba Cloud
- Tencent Cloud
- Volcano Engine
- vLLM Self-HostedSelf-hosted model inference and serving engine with OpenAI-compatible APIs.
- AWS
- Azure
- Google Cloud
These products address related workflows; read their category-fit notes before comparing scope. See all of AI inference & gateways →
Installation outline
- Choose the documented deployment option and a dedicated cloud environment. Follow the launch methodology.
- Review the vendor's installation documentation, required permissions and outbound data flows.
- Deploy to a non-production environment; configure identity, networking and monitoring.
- Test backup recovery and upgrades before promoting to production.
Evidence trail
Every claim on this page traces to the sources below. They document the deployment option; they do not constitute a security certification.
- Deployment sourcesChecked
- Official installation and runtime ↗docs.sglang.io
- Upstream project and capabilities ↗github.com
- Current upstream license ↗raw.githubusercontent.com
- CVE-2026-111391 debug dumper filter code injection ↗nvd.nist.gov
- Upstream SGLang dumper-filter RCE issue ↗github.com
- SGLang v0.5.23 debug dumper implementation ↗github.com
- CVE-2026-111391 primary record and affected-version range ↗cveawg.mitre.org
- Cloud deployment evidenceChecked
The linked sources describe each deployment path, edition and support scope. Community templates and partner statements are identified in the notes.
- SGLang compatibility with GKE Inference Gateway ↗ · Google Cloud
Provider guide · Reviewed 2026-11-12. Vendor support commitment: not assessed; confirm the selected release and contract.
Google explicitly supports SGLang as an alternative model server in its customer-operated multi-cluster GKE inference architecture. The worked manifests use vLLM; SGLang requires its own deployment, serving port, metric mapping and compatible Endpoint Picker image. Review GPU/model requirements, licenses and resource availability.
- SGLang compatibility with GKE Inference Gateway ↗ · Google Cloud
- Infrastructure evidenceChecked
- Licensing evidenceChecked
- Community & maintenance evidenceChecked
- Release maintenance and contributor participation ↗github.com
- Project and production-use context ↗raw.githubusercontent.com