Back to the registry
Agent passport

ExLlama/ExLlamaV3

bCloud LLC · Software Development

Virtual MachinesNo attestation published

Certification per Microsoft Marketplace.

Provenance reach3 of 12 layers traced

Evidence tier Source Confirmed · 9 captures on record

User rating5 ★1 review on the listing
Runs onVirtual MachinesVirtual machine
ProvenanceUnknown33% of the provenance layers this product can disclose
Evidence riskHighSign in to see the basis for this band.

What the publisher says

As described on Microsoft Marketplace.

ExLlama / ExLlamaV3 is a high-performance Python library designed for running large language models (LLMs) efficiently on NVIDIA GPUs. It provides optimized CUDA extensions, fast tokenization, and tensor management to enable low-latency inference for AI and NLP workloads.

Features of ExLlama / ExLlamaV3:

Show the rest of the publisher’s description (12 more lines)
  • GPU-accelerated inference for large language models using optimized CUDA extensions.
  • Support for tokenization and tensor operations for seamless integration with Python workflows.
  • Efficient memory utilization for transformer-based models.
  • Modular design to support NLP tasks such as text generation, summarization, and AI content creation.
  • Easy integration with Python ML pipelines and research projects.

Usage Instruction:

Activate virtual environment:

$ sudo su

$cd /opt/exllamav3

$source exllama-env/bin/activate

Verify ExLlamaV3 version: pip show exllamav3

Disclaimer: ExLlama / ExLlamaV3 is an open-source AI library provided under its respective license. It is offered "as is," without any warranty, express or implied. Users are responsible for ensuring compatibility with their hardware (CUDA-enabled GPUs) and Python environment.

Agent build and provenance

See the full provenance

The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.

Compliance

Government
  • FedRAMPConfirmedNot listed90%, registry-checkedNo FedRAMP Marketplace entry matched this vendor's domain, checked 2026-08-27registry recordas observed 2026-08-27

Confirmed means matched to a public authoritative registry. Claimed means the vendor or its listing states it, not yet cross-checked. A framework not shown was not found in any source we hold, which is not evidence against it. Not listed means a scoped registry check found no match for this vendor's domain: a No is a scoped registry check, not a compliance judgment. Confidence bands: 95% domain-verified, 90% registry-checked, 80% self-attested, 70% weak signal. Self-attested items marked “vendor's site” are gathered from the vendor's own website and are not verified by us.

Vendor

External enrichment · as of 2026-08-29

CompanybCloud AIAutomated
HQUnited States of AmericaVerified
IndustryTechnologyAutomated
Websitehttps://www.bcloud.ai/

Sources

Marketplace listingmarketplace.microsoft.comSource
Privacy PolicyPrivacy PolicySource
License TermsLicense TermsSource

Publisher resources

1 link
Supportbcloud.aiSource

Linked repositories

RepositoriesUnknownUnknown

Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.

Pricing
Unknown
Not stated
Delivery
Virtual machine
https://bcloud.ai/Default.aspx
Open the source listing ↗

Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.