{"slug": "cuda-rocm-dual-back-ends-llm-inference-for-mixed-vendor-gpus-up-to-48-faster", "title": "CUDA+ROCm dual-back ends LLM inference for mixed-vendor GPUs (up to 48% faster)", "summary": "A contributor to the project-maya repository opened a pull request adding a separately built HIP library that lets LLM inference run on NVIDIA and AMD GPUs in the same machine, with the owner reporting up to 48% faster performance. The owner of mw00/project-maya said the change stays off unless the plugin path is set and leaves the normal build and output unchanged, and that the team wants to test it on its own NVIDIA + AMD Linux setup before merging, which \"may take a few days.\" The owner will document the settings under their MAYA_ names, keep the test folder to the parts CI runs, and fit the change on top of the GLM helper work from pull requests #849–#851.", "body_md": "## Repository navigation\n\n## Conversation\n\n[RenWuJun](https://github.com/RenWuJun)\n\n[force-pushed](https://github.com/mw00/project-maya/compare/8ab866d774aae24de90c69dde20adf127cfefaef..bac40a6a1c5eca8b730d0597bdf6259d47118f10)the hengha/glm-hip-helper branch from\n\n[to](https://github.com/mw00/project-maya/commit/8ab866d774aae24de90c69dde20adf127cfefaef)\n\n`8ab866d`\n\n`bac40a6`\n[Compare](https://github.com/mw00/project-maya/compare/8ab866d774aae24de90c69dde20adf127cfefaef..bac40a6a1c5eca8b730d0597bdf6259d47118f10)\n\n[November 6, 2026 02:08](#event-35306876612)\n\nOwner\n\n| Thanks a lot for this - running an NVIDIA card and an AMD GPU together in one PC is something we really want, and the split into a separately built HIP library with a small versioned interface is a clean way to do it. We read it through: it stays off unless the plugin path is set, and the normal build and output don't change. We'd like to run it on our own NVIDIA + AMD Linux setup before we bring it in, so it may take a few days. On our side we'll list the settings under their MAYA_ names in the docs, keep the test folder to the parts CI runs, and fit it on top of the GLM helper changes from [#849](https://github.com/mw00/project-maya/pull/849) -[#851](https://github.com/mw00/project-maya/pull/851) - we'll handle that ourselves. | \n\n      This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.\n      \n\n[Learn more about bidirectional Unicode characters](https://github.co/hiddenchars)\nAdd this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.", "url": "https://wpnews.pro/news/cuda-rocm-dual-back-ends-llm-inference-for-mixed-vendor-gpus-up-to-48-faster", "canonical_source": "https://github.com/mw00/project-maya/pull/879", "published_at": "2026-11-10 02:05:11+00:00", "updated_at": "2026-11-10 02:22:30.509406+00:00", "lang": "en", "topics": ["ai-infrastructure", "large-language-models", "ai-tools", "developer-tools"], "entities": ["project-maya", "RenWuJun", "NVIDIA", "AMD", "CUDA", "ROCm", "HIP", "GLM"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/cuda-rocm-dual-back-ends-llm-inference-for-mixed-vendor-gpus-up-to-48-faster", "markdown": "https://wpnews.pro/news/cuda-rocm-dual-back-ends-llm-inference-for-mixed-vendor-gpus-up-to-48-faster.md", "text": "https://wpnews.pro/news/cuda-rocm-dual-back-ends-llm-inference-for-mixed-vendor-gpus-up-to-48-faster.txt", "jsonld": "https://wpnews.pro/news/cuda-rocm-dual-back-ends-llm-inference-for-mixed-vendor-gpus-up-to-48-faster.jsonld"}}