A developer evaluated speculative decoding in vLLM on AMD Instinct MI300X and MI355X GPUs, testing draft methods including MTP, EAGLE-3, DFlash, and DSpark that propose candidate tokens verified in a …
TileRT powered GLM-5.3 to 469 tok/s of single-user generation throughput on 8× AMD Instinct MI355X GPUs, taking the top spot on the InferenceX AgentX leaderboard and beating the second-place NVIDIA GB…
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 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…
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.…
AMD's experiments with speculative decoding in vLLM on AMD Instinct MI300X and MI355X GPUs using the ROCm platform show that output-token throughput gains vary by drafting method, proposal length, mod…
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, Cisco and HUMAIN, a PIF company, announced that AMD Instinct MI355X GPU-based AI infrastructure built on Cisco Silicon One-based AI networking is now live in Saudi Arabia and serving HUMAIN custo…
On a single 8-GPU AMD Instinct MI355X node, AMD served Kimi Linear 48B-A3B with context lengths from 1024 tokens to 64Mi (67,108,864), using vLLM with FP8 KV cache and tensor parallelism 8, recording …
AMD's ROCm blog published a walkthrough for running verl's asynchronous reinforcement learning examples on AMD Instinct MI355X GPUs, covering GRPO on Qwen2.5-VL-7B-Instruct with the Geometry3k dataset…
AMD announced that its Lux supercomputer, built with AMD Instinct MI355X GPUs, EPYC CPUs, and Pensando networking at Oak Ridge National Laboratory, will become the first fully operational platform for…
AMD shows how to serve the pre-quantized amd/Kimi-K2.5-MXFP4 checkpoint on AMD Instinct MI355X GPUs using ATOM, a lightweight vLLM-like framework that integrates AITER kernels and exposes an OpenAI-co…
AMD has optimized MiniMax-M3 inference on Instinct MI355X GPUs using ATOM, AITER, and ATOMesh, achieving improvements in serving throughput, token latency, and accuracy through online quantization, sp…
AMD announced the acceleration of large-scale LLM inference on its Instinct MI350X/MI355X GPUs using Eagle3 speculative decoding and AMD Quark quantization. The work enables lossless inference speedup…