iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
Short answer: NVIDIA Rubin PCIe GPUs appear to be a planned future option for HPE’s ProLiant DL585a Gen13, but they are not yet a confirmed, orderable HPE configuration. A report published October 12, 2026 says an HPE presentation lists Rubin PCIe GPUs among the accelerators supported by the 10U DL585a. HPE’s current public QuickSpecs and accelerator catalog reviewed for this article do not name a Rubin card or provide its SKU, memory, power draw, dimensions, qualification status, price or release date.
That makes the announcement useful as a platform-direction signal, not as a purchasing specification. Anyone planning a Rubin-based system still needs a named GPU model, an HPE-qualified configuration, firmware support and validated power, cooling, mechanical and software details.
Which HPE server is associated with Rubin PCIe support?
The specific platform identified in the public reporting is the HPE ProLiant DL585a Gen13. It is a 10U, AMD EPYC 9006-series server designed for high-density PCIe acceleration. HPE describes it as supporting up to eight qualified double-wide PCIe GPUs and references NVIDIA’s 2-8-5 architecture.
This does not mean every ProLiant Gen13 model will accept Rubin cards. The reported Rubin listing applies to the DL585a presentation and should not be generalized to other Gen13 servers without a model-specific QuickSpecs entry or configuration guide.
#1 Best Overall
- Read Before You Buy — No Video Output: These adapters support charging and USB 2.0 data transfer, but cannot transmit video signals. Except for standard USB webcams (which use USB data only), they are not compatible with HDMI/DisplayPort cables, video-capable USB-C hubs, or docking stations with video output.
- Convert USB-A Ports to USB-C: Designed to connect USB-C earphones, cables, flash drives, card readers, and other USB-C accessories to standard USB-A ports. Plug-and-play with no drivers or software required.
- Aluminum Alloy Housing: Built with a sturdy aluminum alloy shell that aids in heat dissipation and protects against daily wear and scratches. Designed to maintain a stable and secure connection.
- Compact & Travel-Friendly: The ultra-compact design allows the adapter to stay plugged into your device without blocking adjacent ports or adding bulk, reducing wear and tear on your original USB ports.
- 12-Month Warranty: Backed by a 12-month manufacturer warranty for peace of mind. Designed to meet strict quality control standards for reliable everyday performance.
The Next Platform reported on October 8, 2026 that the DL585a was expected to become available in March 2027 and uses sixth-generation PCI connectivity. That is a server schedule, not a Rubin GPU launch date. A Rubin card could be released before or after the server, and the report does not establish when HPE will publish an orderable Rubin option.
Does the DL585a Gen13 officially support Rubin PCIe GPUs?
There are two different levels of evidence:
- Reported platform indication: An October 12, 2026 report says an HPE presentation lists Rubin PCIe GPUs as supported by the DL585a Gen13.
- Public product qualification: HPE’s current DL585a QuickSpecs and NVIDIA accelerator catalog reviewed here list current products such as the NVIDIA RTX PRO 6000 Blackwell Server Edition 96GB PCIe, RTX PRO 6000D 84GB PCIe, H200 NVL and L40S, but do not name a Rubin PCIe model.
Until HPE publishes a Rubin SKU in the DL585a QuickSpecs, a supported configurator entry or an equivalent qualification document, treat compatibility as reported future support. It is not evidence that a customer can order a Rubin-equipped DL585a today.
What is a Rubin PCIe GPU?
Rubin is NVIDIA’s announced AI platform, named for astronomer Vera Rubin. NVIDIA describes a platform built around six chips and technologies including NVLink, Transformer Engine, Confidential Computing, a reliability, availability and serviceability (RAS) engine and the Vera CPU. NVIDIA also names HPE among the companies expected to adopt the Rubin platform.
Recommended Free Tools
Those statements describe the broader Rubin architecture. They do not define a particular PCIe add-in card. A rack-scale Rubin system, a SXM-style module and a double-wide PCIe board can have different memory, cooling, power, interconnect and firmware requirements. Specifications from one form factor must not be transferred to another.
Rank #2
- 5-in-1 USB-C Hub: Experience comprehensive connectivity featuring a Power Delivery input, two USB-A 2.0 ports, a USB-A 3.0 port, and an HDMI port. (Note: The USB-C power delivery input port is only for connecting an external wall charger to power your laptop and cannot power peripheral devices.)
- 90W Pass-Through Charging: Achieve optimal charging with 90W pass-through power to your laptop, supported by a total input of 100W, with the hub reserving 10W for operational efficiency. (Note: Wall charger not included.)
- Quick Data Transfers: Accelerate your productivity with rapid data transfers using a high-speed 5Gbps USB 3.0 port and two 480Mbps USB 2.0 ports.
- 4K HDMI Display: Enhance your visual experience with a hub capable of delivering 4K resolution at 30Hz in both mirror and extend modes. Please note that this hub is compatible with MacBook (macOS 12 and newer), Windows 10 and 11, ChromeOS, and laptops equipped with DP Alt Mode and Power Delivery. Note: This device is not compatible with Linux.
- What You Get: Anker USB-C Hub (5-in-1, 4K HDMI), welcome guide, 18-month warranty, and our friendly customer service.
NVIDIA has announced a claim of “up to 10x lower cost per token” compared with its Blackwell platform. That is an NVIDIA platform claim, not a measured result for a Rubin PCIe card in a DL585a Gen13. No public source reviewed here provides a DL585a Rubin benchmark.
What the DL585a Gen13 can accommodate today
HPE’s platform rules are clearer than the Rubin card details. The server is designed around qualified double-wide PCIe accelerators and permits these GPU counts:
| DL585a GPU configuration | What HPE states |
|---|---|
| 0 GPUs | Supported platform configuration |
| 1 GPU | Supported when the selected model and system configuration are qualified |
| 2 GPUs | Supported qualified configuration |
| 4 GPUs | Supported qualified configuration |
| 8 GPUs | Maximum stated count for qualified double-wide PCIe GPUs |
HPE says different GPU models cannot be mixed in one DL585a configuration. An eventual Rubin card therefore should not be assumed to work alongside a currently listed Blackwell, H200 NVL or L40S card unless HPE explicitly documents that combination.
Crashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minutePC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11HPE also lists a switchboard enablement kit with 12 PCIe slots, a full-height, full-length (FHFL) GPU cage kit and the DL585a GPU Power Cable Kit, part number P97059-B21. These are platform enablement components; having the slot count or cable kit does not by itself qualify an unlisted GPU.
Rank #3
- Sleek 7-in-1 USB-C Hub: Features an HDMI port, two USB-A 3.0 ports, and a USB-C data port, each providing 5Gbps transfer speeds. It also includes a USB-C PD input port for charging up to 100W and dual SD and TF card slots, all in a compact design.
- Flawless 4K@60Hz Video with HDMI: Delivers exceptional clarity and smoothness with its 4K@60Hz HDMI port, making it ideal for high-definition presentations and entertainment. (Note: Only the HDMI port supports video projection; the USB-C port is for data transfer only.)
- Double Up on Efficiency: The two USB-A 3.0 ports and a USB-C port support a fast 5Gbps data rate, significantly boosting your transfer speeds and improving productivity.
- Fast and Reliable 85W Charging: Offers high-capacity, speedy charging for laptops up to 85W, so you spend less time tethered to an outlet and more time being productive.
- What You Get: Anker USB-C Hub (7-in-1), welcome guide, 18-month warranty, and our friendly customer service.
What Rubin support means for buyers and system architects
A Rubin reference in an HPE presentation can influence planning, but it does not answer the engineering questions needed for a purchase. A valid design review should confirm every item below against an HPE document for the exact card:
- GPU identity: official model name, HPE option or SKU and NVIDIA product designation.
- Memory: capacity, memory type and bandwidth.
- Power: board power, peak or transient requirements, connector type and the number of cards supported at the selected CPU and storage configuration.
- Mechanical fit: double-wide or other width, full-height/full-length dimensions, bracket style, cable clearance and approved slot positions.
- PCIe requirements: generation, lane width, bifurcation or switch requirements and whether all eight positions can operate at the stated link speed simultaneously.
- GPU interconnect: whether the card uses NVLink or another fabric, what bridge or switch hardware is needed and which topologies HPE supports.
- Thermal design: air-flow direction, inlet temperature limits, fan requirements and whether a fully populated chassis needs special cooling options.
- Firmware and software: system ROM, GPU firmware, driver branch, Linux or Windows support and any HPE management integration.
- Availability: order date, lead time, regional restrictions and supported service coverage.
Most of these Rubin-specific values are not stated in the public material reviewed for this article. Do not fill the gaps with specifications from a rack-scale Rubin announcement or from another NVIDIA form factor.
Why the DL585a is a 10U, air-cooled design
HPE positions the DL585a for AI inference, agentic AI, retrieval-augmented generation (RAG), fine-tuning, analytics and visualization. HPE Compute vice president John Carter told The Next Platform that PCIe GPU customers often run out of electrical capacity before they run out of chassis space: “Most of our customers who are using a PCIe-type GPU, what they’re really telling us is, ‘We’re running out of power long before we run out of space, so make it bigger.’”
The larger 10U enclosure and air-cooled orientation are therefore connected to power delivery and thermal headroom for dense PCIe configurations. This is vendor positioning rather than independent performance testing. A Rubin board could change the power and cooling balance, so the DL585a’s current chassis capability should not be treated as proof that every future Rubin configuration will run at eight cards.
Rank #4
- Dual Converters, Infinite Potential：Includes 2× USB C male to USB A female adapters and 2× USB A male to USB C female adapters. Perfect for a wide range of uses—tablets with Bluetooth keyboards, expand USB ports on macbook, and more. Two different converters for all your daily needs
- Next-Level 10Gbps & 3A Charging: No more slow 480Mbps, this usb to usb c adapter has a transfer speed of up to 10Gbps, allowing you to do more transferring in less time. This usb adapter fits both USB A and USB C charger, supporting up to 3A fast charging
- Upgraded Exquisite Craftsmanship: With an aluminum alloy housing and metal connector, the usbc to usb adapter is extremely durable and sturdy. Rigorously tested to withstand more than 10,000 times of plugging and unplugging, ensuring long-lasting performance
- Broad Compatible: The usb c to usb adapter widely supports all USB C/ USB A devices like laptops, tablets, cellphones, car chargers, and phone chargers. Such as compatible with MacBook Pro/Air 2023/2022, Thunderbolt 4/3 Devices,Apple MagSafe Watch 9/8/7/SE/Ultra, iPad Pro 2022/2021, Samsung Galaxy S23/S20/S10, and iPhone 17/16/15 Pro. Plug and play
- Please Note: To reach 10Gbps speed, keep the cable under 3.3 ft. For USB A Male to USB C adapters, try flipping the USB C connector. USB C Male to USB A adapters support bidirectional 10Gbps transfer within 3.3 ft
Carter described the intended market as “more for the enterprise, for the mid-tier service providers, those kinds of folks.” He also emphasized that scale introduces security and management concerns: “That kind of scale and performance brings new security risks,” and “It brings new complexity in terms of managing many, many systems.”
How Rubin compares with currently listed DL585a accelerators
The comparison below separates documented current options from unknown Rubin details.
| Attribute | Current HPE-listed examples | Rubin PCIe in the reported DL585a listing |
|---|---|---|
| Named products | RTX PRO 6000 Blackwell Server Edition 96GB PCIe; RTX PRO 6000D 84GB PCIe; H200 NVL; L40S and others | No public model name or SKU stated |
| HPE qualification | Covered by the relevant QuickSpecs or accelerator documentation | Reported in an HPE presentation; current public QuickSpecs reviewed do not list it |
| Memory capacity | Model-specific values are documented for listed products | Not stated in the public sources reviewed |
| Power draw and connectors | Model-specific values appear in product documentation | Not stated |
| Physical dimensions and slot placement | Defined by each qualified configuration | Not stated |
| PCIe generation and interconnect | Defined by each product and DL585a configuration | Not stated for a Rubin PCIe card |
| Price and availability | Depends on region, configuration and HPE quotation | No Rubin price or release date stated |
The absence of a Rubin value is meaningful: it prevents a responsible buyer from calculating rack power, cooling load, usable memory or performance per dollar.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
Will Rubin GPUs work in other HPE ProLiant Gen13 servers?
There is no basis to assume that. PCIe electrical compatibility alone is insufficient for a supported server configuration. Each ProLiant model has its own slot layout, riser design, power budget, fan curve, firmware and GPU qualification matrix.
Best Value
- 5-in-1 Connectivity: Equipped with a 4K HDMI port, a 5 Gbps USB-C data port, two 5 Gbps USB-A ports, and a USB C 100W PD-IN port. Note: The USB C 100W PD-IN port supports only charging and does not support data transfer devices such as headphones or speakers.
- Powerful Pass-Through Charging: Supports up to 85W pass-through charging so you can power up your laptop while you use the hub. Note: Pass-through charging requires a charger (not included). Note: To achieve full power for iPad, we recommend using a 45W wall charger.
- Transfer Files in Seconds: Move files to and from your laptop at speeds of up to 5 Gbps via the USB-C and USB-A data ports. Note: The USB C 5Gbps Data port does not support video output.
- HD Display: Connect to the HDMI port to stream or mirror content to an external monitor in resolutions of up to 4K@30Hz. Note: The USB-C ports do not support video output.
- What You Get: Anker 332 USB-C Hub (5-in-1), welcome guide, our worry-free 18-month warranty, and friendly customer service.
Use the DL585a reference only for the DL585a. For another Gen13 model, look for an HPE QuickSpecs entry that names the exact Rubin card and lists the required enablement kits. If the model is absent, ask HPE or an authorized integrator for written confirmation before designing around it.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.When will Rubin PCIe cards be available?
No Rubin PCIe availability date is established by the public sources reviewed. The Next Platform’s March 2027 expectation concerns DL585a server availability. It should not be presented as the Rubin card’s launch date.
NVIDIA states that Rubin platform features, pricing, availability and specifications can change. HPE’s own configuration documents can also change as qualification work is completed. A procurement schedule should therefore use a named HPE option, a quoted lead time and a current support statement rather than the presentation reference alone.
How to validate a Rubin-ready DL585a configuration
- Identify the exact accelerator. Require an NVIDIA model name and an HPE option or SKU. “Rubin PCIe” without a model number is not sufficient.
- Check the current DL585a QuickSpecs. Confirm that the card appears in the GPU list for the intended region and system build.
- Verify the count rule. Select one of HPE’s supported counts—0, 1, 2, 4 or 8—and confirm that no mixed-GPU restriction is violated.
- Confirm enablement hardware. Check the switchboard, riser or cage requirements and whether P97059-B21 or another cable kit is required.
- Calculate electrical load. Use the card’s documented board and transient power, then include CPUs, memory, drives, fans and networking. Do not substitute a rack-scale Rubin figure.
- Validate airflow and placement. Confirm approved slots, clearances, inlet temperature and fan settings for the selected population.
- Match software support. Verify system ROM, GPU firmware, driver versions, operating-system support and management tools.
- Obtain a supportable quote. Ensure the quotation includes the exact GPU, chassis, power supplies, enablement kits and service coverage.
- Recheck before shipment. Forward-looking products can change between a presentation and a final QuickSpecs release.
What workloads could benefit from a Rubin PCIe option?
The DL585a’s stated workload targets include inference, agentic AI, RAG, fine-tuning, analytics and visualization. A PCIe Rubin option could be relevant where an organization wants accelerator capacity in a conventional server rather than a specialized rack-scale system.
Actual suitability will depend on the final card’s memory capacity, bandwidth, interconnect topology, software support and power envelope. For example, a workload that needs fast GPU-to-GPU communication may depend more on the supported NVLink or fabric topology than on the number of PCIe slots. A memory-heavy inference service may be constrained by card capacity even if the chassis can hold eight boards.
Without a Rubin PCIe benchmark in the DL585a, it is not possible to claim a particular throughput, latency, cost-per-token or energy advantage for this server.
What is known—and still unknown
| Question | Current answer |
|---|---|
| Which server is implicated? | HPE ProLiant DL585a Gen13 |
| How many GPUs can it support? | Up to eight qualified double-wide PCIe GPUs |
| Can different GPU models be mixed? | HPE says no |
| Is Rubin named in current public QuickSpecs? | No, based on the documents reviewed |
| Is there a reported HPE presentation listing Rubin PCIe? | Yes, according to an October 12, 2026 report |
| When is the DL585a expected? | The Next Platform reported March 2027 |
| When is a Rubin PCIe card shipping? | Not established |
| What are Rubin PCIe memory, power and dimensions? | Not stated in the public sources reviewed |
| Is there a DL585a Rubin benchmark? | No named benchmark was published in the reviewed sources |
Bottom line for planning
The Rubin reference matters because it suggests HPE is preparing the DL585a Gen13 for a future generation of NVIDIA PCIe acceleration. It does not yet turn the server into a purchasable Rubin system. Treat the October 2026 report as an early compatibility signal, keep current Blackwell and other listed accelerators as the documented baseline, and wait for an exact Rubin SKU and HPE qualification before committing to mechanical, electrical, software or financial assumptions.
Free tools Windows power users keep installed
One-click scans. No signup required.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
