AMD introduced the TraceLens Agent, an autonomous performance bottleneck identification system that converts raw PyTorch profiler traces into a prioritized, evidence-backed optimization report. The ag…
AMD detailed its AMD Inference Microservices (AIMs), standardized Docker-based inference microservices that automatically select a runtime profile from inputs including model, precision, engine, laten…
AMD demonstrated that Ai2's open-source MolmoAct2 vision-language-action model can run entirely on a single AMD Ryzen AI Max+ 395 "Strix Halo" mini PC using the ROCm software stack, with no cloud or e…
AMD reported that UltraQuant, its 4-bit KV-cache method for the Qwen3.8-2.4T MXFP4 model on AMD Instinct MI355X GPUs, serves 29% more tokens per second at 24% lower per-token latency than the fastest …
AMD detailed model weight profiles that break down how many parameters go to embeddings, attention, and dense layers, explaining why the amd/Llama-3.1-8B-Instruct-FP8-KV checkpoint is 9.08 GB rather t…
AMD detailed a local quantization workflow using AMD Quark 0.12.post1 that compressed the Qwen3.6-35B-A3B Mixture-of-Experts model from BF16 to W4A16 on a single Strix Halo system, cutting model weigh…
A new technical blog post details a three-way logprob comparison method for debugging probability mismatches between the rollout engine and trainer in online reinforcement learning for large language …
Moonshot AI released the weights for Kimi-K3, a 2.8-trillion-parameter, 1M-context, natively-MXFP4 Mixture-of-Experts model, with AMD Instinct support available on day 0 across three serving framework…
AMD researchers introduced Zebra-HyLo, an upcycling recipe that converts pretrained Transformer models into long-context hybrid LLMs through post-training on roughly 10B tokens, without pretraining fr…
AMD released ROCm Hyperloom, an open-source multi-agent harness that delivered a median 1.73× inference speedup on AMD Instinct GPUs, with gains ranging from 1.35× to 7.31× in unattended evaluation. T…
AMD reported leadership scores and expanded benchmark coverage in MLPerf Inference v6.1, whose results were released on September 16, 2026. AMD and its partners submitted validated results across dlrm…
AMD published a step-by-step recipe for reproducing its MLPerf Inference v6.1 submission results on AMD Instinct MI355X, MI350X, and MI350P GPUs, marking the company's fifth consecutive round of MLPer…
AMD published a step-by-step FlyDSL workflow for implementing a custom diffusion attention kernel, targeting vLLM's TiDAR (Think in Diffusion, Talk in Autoregression) mode with paged KV caches and scr…
DFlash, a block-diffusion speculative decoding drafter, delivered up to 5.02× single-request throughput on Qwen3.5-27B when run on AMD Instinct MI355X through vLLM on ROCm, according to the benchmark.…
A two-stage agentic pipeline combining GLM-4.7-Flash, a 30B tool-calling model, with Poro2, a 70-billion-parameter Finnish-language model, enriches medical terminology via Model Context Protocol tools…
AMD's Helios GPU, the Instinct MI455X, packs 432 GB of HBM4, 23 TB/s of HBM bandwidth per GPU, and 40 PFLOPs of FP4 compute, according to AMD's product brochure. A new educational blog post builds a l…
AMD and the veRL project released a production-ready reinforcement learning post-training container for AMD Instinct GPUs, supporting MI300 and MI355 series on ROCm, with AITER-accelerated vLLM and SG…
DeepSeek-AI released the DeepSeek-V4 series on April 24, 2026, including the MIT-licensed DeepSeek-V4-Flash model with 284B total parameters (13B activated) and a one-million-token context window, and…
AMD's ATOM and vLLM-ATOM inference engines were optimized for high-interactivity LLM inference, targeting responsiveness for single users rather than batch throughput. The optimizations focus on remov…
AMD released ROCm 10.0, the first major version bump since the 7.x series, built entirely on TheRock automated build system and introducing ROCm.AI, a native agentic AI developer experience. The relea…