Skip to content

docs(gpu-support): add HEVC encode column and popular AI GPU section #868

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
DeveloperAlly merged 2 commits into from
Apr 7, 2026
Merged

docs(gpu-support): add HEVC encode column and popular AI GPU section #868

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9af8b08
Initial plan
Copilot Apr 7, 2026
88de291
docs(gpu-support): add HEVC encode column and popular AI GPU section
Copilot Apr 7, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
113 changes: 109 additions & 4 deletions v2/orchestrators/resources/gpu-support.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,8 @@ keywords:
- session limits
- RTX
- transcoding
- HEVC
- H.265
- AI inference
'og:image': /snippets/assets/site/og-image/en/orchestrators.png
'og:image:alt': Livepeer Docs social preview image for Orchestrators
Expand All @@ -23,7 +25,7 @@ pageType: reference
audience: orchestrator
purpose: reference
status: review
lastVerified: 2026-03-13
lastVerified: 2026-04-07
---
{/* TODO:
Terminology Validation:
Expand Down Expand Up @@ -64,79 +66,92 @@ go-livepeer requires NVIDIA GPUs with NVENC and NVDEC support. AMD and Intel GPU
<TableRow header>
<TableCell header>GPU Family</TableCell>
<TableCell header>Transcoding</TableCell>
<TableCell header>HEVC Encode</TableCell>
<TableCell header>AI Inference</TableCell>
<TableCell header>Notes</TableCell>
</TableRow>
<TableRow>
<TableCell>**GeForce RTX 40xx** (Ada Lovelace)</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Best consumer option. AV1 encode support.</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Best consumer option. AV1 and HEVC 10-bit encode support.</TableCell>
</TableRow>
<TableRow>
<TableCell>**GeForce RTX 30xx** (Ampere)</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Widely used by orchestrators. Good price-performance.</TableCell>
</TableRow>
<TableRow>
<TableCell>**GeForce RTX 20xx** (Turing)</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Supported but older.</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Supported but older. HEVC B-frames supported.</TableCell>
</TableRow>
<TableRow>
<TableCell>**GeForce GTX 16xx** (Turing)</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Limited</TableCell>
<TableCell>No Tensor cores — AI inference slower or unsupported for some pipelines.</TableCell>
<TableCell>No Tensor cores - AI inference slower or unsupported for some pipelines.</TableCell>
</TableRow>
<TableRow>
<TableCell>**GeForce GTX 10xx** (Pascal)</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Limited</TableCell>
<TableCell>Legacy. NVENC Gen 6. No Tensor cores.</TableCell>
</TableRow>
<TableRow>
<TableCell>**Tesla T4**</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Data centre card. 16 GB VRAM. Common in cloud.</TableCell>
</TableRow>
<TableRow>
<TableCell>**Tesla V100**</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Data centre. 16/32 GB VRAM.</TableCell>
</TableRow>
<TableRow>
<TableCell>**A100**</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Data centre. 40/80 GB VRAM. Highest throughput.</TableCell>
</TableRow>
<TableRow>
<TableCell>**A10 / A10G**</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Cloud-optimised (AWS G5, etc.). 24 GB VRAM.</TableCell>
</TableRow>
<TableRow>
<TableCell>**L4**</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Ada Lovelace data centre. 24 GB VRAM. Good for AI.</TableCell>
</TableRow>
<TableRow>
<TableCell>**L40 / L40S**</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Yes</TableCell>
<TableCell>48 GB VRAM. High-end AI and transcoding.</TableCell>
</TableRow>
<TableRow>
<TableCell>**H100**</TableCell>
<TableCell>Transcoding works but overkill</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Yes</TableCell>
<TableCell>80 GB VRAM. Primarily for LLM and large model inference.</TableCell>
</TableRow>
</StyledTable>
Expand Down Expand Up @@ -314,6 +329,96 @@ For detailed per-pipeline VRAM planning, see the [Model and Demand Reference](/v

<CustomDivider />

## Popular GPUs for AI Workloads

The following GPUs are well-suited for AI inference on the Livepeer network. VRAM is the primary constraint - larger models require more VRAM, and running multiple warm models simultaneously multiplies the requirement.

<StyledTable variant="bordered">
<TableRow header>
<TableCell header>GPU Model</TableCell>
<TableCell header>VRAM</TableCell>
<TableCell header>HEVC Encode</TableCell>
<TableCell header>Best For</TableCell>
<TableCell header>Notes</TableCell>
</TableRow>
<TableRow>
<TableCell>**RTX 4090**</TableCell>
<TableCell>24 GB</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Image/video AI, quantised LLMs</TableCell>
<TableCell>Top consumer GPU. High throughput for diffusion models.</TableCell>
</TableRow>
<TableRow>
<TableCell>**RTX 3090 / 3090 Ti**</TableCell>
<TableCell>24 GB</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Image/video AI, quantised LLMs</TableCell>
<TableCell>Best value 24 GB option. Widely used in the Livepeer network.</TableCell>
</TableRow>
<TableRow>
<TableCell>**RTX 4070 Ti Super**</TableCell>
<TableCell>16 GB</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Single warm AI model + transcoding</TableCell>
<TableCell>Good balance of price, power, and VRAM.</TableCell>
</TableRow>
<TableRow>
<TableCell>**RTX 4080 Super**</TableCell>
<TableCell>16 GB</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Single warm AI model + transcoding</TableCell>
<TableCell>Higher CUDA core count than 4070 Ti Super.</TableCell>
</TableRow>
<TableRow>
<TableCell>**Tesla T4**</TableCell>
<TableCell>16 GB</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Cloud AI inference</TableCell>
<TableCell>Efficient data centre card. Common in AWS/GCP/Azure.</TableCell>
</TableRow>
<TableRow>
<TableCell>**A10G**</TableCell>
<TableCell>24 GB</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Cloud AI inference + transcoding</TableCell>
<TableCell>AWS G5 instance GPU. Strong diffusion model performance.</TableCell>
</TableRow>
<TableRow>
<TableCell>**L4**</TableCell>
<TableCell>24 GB</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Cloud AI inference + transcoding</TableCell>
<TableCell>Ada Lovelace. Efficient power draw. Common in GCP.</TableCell>
</TableRow>
<TableRow>
<TableCell>**L40S**</TableCell>
<TableCell>48 GB</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Multi-model AI, large LLMs</TableCell>
<TableCell>48 GB VRAM allows multiple warm models simultaneously.</TableCell>
</TableRow>
<TableRow>
<TableCell>**A100 SXM/PCIe**</TableCell>
<TableCell>40/80 GB</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Large LLMs, high-throughput inference</TableCell>
<TableCell>Data centre. Highest AI throughput available at scale.</TableCell>
</TableRow>
<TableRow>
<TableCell>**H100 SXM/PCIe**</TableCell>
<TableCell>80 GB</TableCell>
<TableCell>Yes</TableCell>
<TableCell>Very large LLMs, maximum throughput</TableCell>
<TableCell>Data centre. ~3x faster than A100 for LLM inference.</TableCell>
</TableRow>
</StyledTable>

<Info>
For orchestrators running both AI pipelines and video transcoding, prioritise VRAM when selecting a GPU. A 24 GB card such as the RTX 3090, A10G, or L4 provides headroom for one or two warm AI models alongside active transcoding sessions.
</Info>

<CustomDivider />

## See Also

<CardGroup cols={3}>
Expand Down
Loading
Loading