# Docs
**URL:** https://devcommunity.amd.com/c/rocm-developers/getting-started-rocm/docs-rocm/158.md
[Latest](https://devcommunity.amd.com/latest.md) · [Categories](https://devcommunity.amd.com/categories.md) · [Tags](https://devcommunity.amd.com/tags.md)
---
## [Accelerating LLM Inference on AMD GPUs with Low-Latency GEMMs](https://devcommunity.amd.com/t/accelerating-llm-inference-on-amd-gpus-with-low-latency-gemms/669)
**Author:** [@nirth\_AMD](https://devcommunity.amd.com/u/nirth_AMD)\
**Replies:** 0\
**Last updated:** [July 1, 2026, 9:58am UTC](https://devcommunity.amd.com/t/accelerating-llm-inference-on-amd-gpus-with-low-latency-gemms/669 "2026-07-01T09:58:12Z")
Large language model inference is becoming increasingly interactive. Users expect chatbots, coding assistants, agents, and real-time copilots to respond quickly, stream tokens smoothly, and stay responsive under concu…
---
## [Technical Dive into AMD’s MLPerf Training v6.0 Submission](https://devcommunity.amd.com/t/technical-dive-into-amd-s-mlperf-training-v6-0-submission/620)
**Author:** [@nirth\_AMD](https://devcommunity.amd.com/u/nirth_AMD)\
**Replies:** 0\
**Last updated:** [June 17, 2026, 1:13pm UTC](https://devcommunity.amd.com/t/technical-dive-into-amd-s-mlperf-training-v6-0-submission/620 "2026-06-17T13:13:48Z")
AMD is proud to share its MLPerf Training v6.0 results, marking another step forward in our commitment to delivering competitive AI training performance using the latest AMD Instinct GPUs. This round covers three benchm…
---
## [Accelerating ComfyUI Workflows on AMD Instinct™ MI355X GPUs with ROCm](https://devcommunity.amd.com/t/accelerating-comfyui-workflows-on-amd-instinct-mi355x-gpus-with-rocm/521)
**Author:** [@Uncy\_AMD](https://devcommunity.amd.com/u/Uncy_AMD)\
**Replies:** 0\
**Last updated:** [May 12, 2026, 9:15am UTC](https://devcommunity.amd.com/t/accelerating-comfyui-workflows-on-amd-instinct-mi355x-gpus-with-rocm/521 "2026-05-12T09:15:19Z")
ComfyUI is an open-source, graphical node-based interface for building generative AI workflows using diffusion models. With over 100,000 stars on GitHub, it has become one of the most widely adopted tools for text-to-…
---
## [MaxText-Slurm: Production-Grade LLM Training with Built-In Observability](https://devcommunity.amd.com/t/maxtext-slurm-production-grade-llm-training-with-built-in-observability/393)
**Author:** [@Uncy\_AMD](https://devcommunity.amd.com/u/Uncy_AMD)\
**Replies:** 0\
**Last updated:** [March 5, 2026, 10:48am UTC](https://devcommunity.amd.com/t/maxtext-slurm-production-grade-llm-training-with-built-in-observability/393 "2026-03-05T10:48:13Z")
Training large language models (LLMs) at scale on GPU clusters is not just a compute problem — it is an operations problem. Launching multi-node distributed training, keeping it running reliably, and diagnosing failures …
---
## [Exploring Use Cases for Scalable AI: Implementing Ray with ROCm 7 Support for Efficient ML Workflows](https://devcommunity.amd.com/t/exploring-use-cases-for-scalable-ai-implementing-ray-with-rocm-7-support-for-efficient-ml-workflows/390)
**Author:** [@Uncy\_AMD](https://devcommunity.amd.com/u/Uncy_AMD)\
**Replies:** 0\
**Last updated:** [March 2, 2026, 12:05pm UTC](https://devcommunity.amd.com/t/exploring-use-cases-for-scalable-ai-implementing-ray-with-rocm-7-support-for-efficient-ml-workflows/390 "2026-03-02T12:05:31Z")
This blog builds on insights from our previous blog post, which introduced Ray 2.48.0.post0 running on ROCm 6.2 and demonstrated Reinforcement Learning from Human Feedback (RLHF) with verl 0.3.0.post0 and vLLM 0.6.4 o…
---
## [Autoscaling with Ray, ROCm 7.0.0, and SkyPilot](https://devcommunity.amd.com/t/autoscaling-with-ray-rocm-7-0-0-and-skypilot/336)
**Author:** [@Uncy\_AMD](https://devcommunity.amd.com/u/Uncy_AMD)\
**Replies:** 0\
**Last updated:** [February 16, 2026, 10:57am UTC](https://devcommunity.amd.com/t/autoscaling-with-ray-rocm-7-0-0-and-skypilot/336 "2026-02-16T10:57:38Z")
This blog explores autoscaling of inference workloads in Ray Serve with a vLLM backend on AMD Instinct™ GPUs for large language models (LLMs). Furthermore, you will learn how to scale beyond a single cluster using Sky…
---
## [Fast Multi-Model Deployment and Validation with JSON-Driven Configuration](https://devcommunity.amd.com/t/fast-multi-model-deployment-and-validation-with-json-driven-configuration/302)
**Author:** [@Uncy\_AMD](https://devcommunity.amd.com/u/Uncy_AMD)\
**Replies:** 0\
**Last updated:** [January 16, 2026, 9:15am UTC](https://devcommunity.amd.com/t/fast-multi-model-deployment-and-validation-with-json-driven-configuration/302 "2026-01-16T09:15:47Z")
Artificial intelligence is no longer limited to single-model applications. In many real-world scenarios, multiple models need to work together to deliver a seamless user experience. This is especially true for applicati…