#MI355
LightNews LightNews
minaxlab.bsky.social
The latest vLLM release, version 0.30.1rc0, brings significant enhancements for #AMD #GPU users. The update adds kernel mirrors for the MI355 accelerator, supporting both dense and Mixture of Experts (MoE) model architectures

#ai

www.minaxlab.com/blog/vllm-mi...
vLLM v0.30.1rc0 Adds MI355 GPU Support for Dense and MoE Models
vLLM 0.30.1rc0 introduces ROCm kernel mirrors for AMD MI355 GPUs, enabling optimized inference for dense and Mixture of Experts models.
www.minaxlab.com
September 25, 2026 at 3:28 AM
techmeme.com
Korean AI startup Upstage says it is in talks to acquire 10K of AMD's MI355 chips, in a bid to "diversify to other chips" as "we have a lot of Nvidia chips" (Bloomberg)

Main Link | Techmeme Permalink
March 23, 2026 at 10:05 AM
wealthwise-dca.bsky.social
AMD CEO Lisa Su Predicts AI Inference Demand to Soar Over 80% Annually

#AMD #AMDStock #AMDNews #AMDStockNews #NVDA #GPUs #MI350 #MI355 #AMDMI350 #AMDMI355 #Semiconductors #AIChips #Microchips
$AMD
June 13, 2025 at 3:03 PM
technology-news.bsky.social
$3 Million USD dataset open sourced, 1 Mil+ Context Length, Multiturn, Sub Agents 95%+ KVCache HitRate, GB300 NVL72, MI355, B200
AgentX - InferenceXv3: Does CUDA Moat Hold up in Agentic Inferencing?
newsletter.semianalysis.com
August 25, 2026 at 10:01 AM
modular.com.web.brid.gy
Modular: Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
www.modular.com
October 18, 2025 at 6:23 PM
modular.com.web.brid.gy
Modular: Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
www.modular.com
October 17, 2025 at 6:23 PM
modular.com.web.brid.gy
Modular: Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
www.modular.com
October 30, 2025 at 6:26 PM
modular.com.web.brid.gy
Modular: Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
www.modular.com
October 29, 2025 at 6:26 PM
modular.com.web.brid.gy
Modular: Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
www.modular.com
October 27, 2025 at 6:25 PM
modular.com.web.brid.gy
Modular: Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
www.modular.com
October 26, 2025 at 6:24 PM
modular.com.web.brid.gy
Modular: Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
www.modular.com
October 28, 2025 at 6:25 PM
genticnews.bsky.social
SemiAnalysis Open-Sources $3M Agentic Inference Dataset

SemiAnalysis open-sourced a $3M agentic inference dataset targeting GB300 NVL72, MI355, B200. It tests whether CUDA's moat holds under 1M+ context, multiturn workloads.

https://gentic.news/article/semianalysis-open-sources-3m
SemiAnalysis Open-Sources $3M Agentic Inference Dataset
SemiAnalysis open-sources $3M agentic inference dataset targeting GB300 NVL72, MI355, B200, testing CUDA's moat with 1M+ context and 95%+ KVCache hit rates.
gentic.news
August 25, 2026 at 4:26 PM
mengli512.bsky.social
#AMD Q2 revenue hit a record $7.7B, with new AI inference chip MI355 delivering 35x performance boost. AMD raises Q3 guidance to $8.7B (excluding $1.5B restricted China sales). NVIDIA CEO forecasts 50% global AI growth, China market to reach $50B this year. open.substack.com/pub/frontier...
AMD: Nvidia Signals a Lasting Boom in Artificial Intelligence
AMD Q2 revenue hits record $7.7B, up 32%. New MI355 AI chip drives inference shift, targeting $8.7B Q3 sales. AI chip market to hit $1T by 2028.
open.substack.com
September 4, 2025 at 7:07 AM
handle.invalid
AgentX - InferenceXv3: Does CUDA Moat Hold up in Agentic Inferencing?
AgentX - InferenceXv3: Does CUDA Moat Hold up in Agentic Inferencing?
$3 Million USD dataset open sourced, 1 Mil+ Context Length, Multiturn, Sub Agents 95%+ KVCache HitRate, GB300 NVL72, MI355, B200
newsletter.semianalysis.com
September 2, 2026 at 7:19 PM
rwceo.bsky.social
用4个Mi355 运行 Kimi-K2.5-MXFP4（MXFP4 量化版本), 4 Bits, 160GB, 无需软件解压, 计算时保持低精度, 节省带宽和算力, 启动参数里还有针对 AMD 的优化
--attention-backend ROCM_AITER_MLA
--kernel-config.enable_flashinfer_autotune false
--enforce-eager
用Kimi Code做简单工作目前感觉ok
August 22, 2026 at 11:05 PM
rwang0.bsky.social
MyPOV: @AnthropicAI to be deploying 2GW's of @amd #helios says Tom Brown to Lisa Su #AMDAdvancingAI

Anthropic likes the AMD Instinct MI355
July 23, 2026 at 4:54 PM
pytorch.org
AMD and Meta contributors detail the ROCm port that brings PyTorch Monarch to AMD Instinct GPUs.

Validation includes Llama 3 8B on 128 GPU MI300 and 256 GPU MI355 clusters.

https://pytorch.org/blog/bringing-pytorch-monarch-to-amd-gpus-single-controller-distributed-training-on-rocm/
July 7, 2026 at 5:00 PM
modular.com.web.brid.gy
Modular: Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
www.modular.com
October 25, 2025 at 6:24 PM
modular.com.web.brid.gy
Modular: Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
www.modular.com
October 24, 2025 at 6:24 PM
modular.com.web.brid.gy
Modular: Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
www.modular.com
October 23, 2025 at 6:24 PM
modular.com.web.brid.gy
Modular: Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
www.modular.com
October 22, 2025 at 6:24 PM
modular.com.web.brid.gy
Modular: Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
www.modular.com
October 21, 2025 at 6:23 PM
modular.com.web.brid.gy
Modular: Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
www.modular.com
October 20, 2025 at 6:24 PM
modular.com.web.brid.gy
Modular: Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
Achieving State-of-the-Art Performance on AMD MI355 — in Just 14 Days
www.modular.com
October 19, 2025 at 6:23 PM