MI355x
PulseAugur coverage of MI355x — every cluster mentioning MI355x across labs, papers, and developer communities, ranked by signal.
- 2026-07-30 research_milestone Kernel optimizations improved MI355X performance by over 2x and were upstreamed to AMD's AITER and ATOM inference engines. source
6 day(s) with sentiment data
-
Kimi K3's 2.8T parameters highlight LLM deployment as a systems engineering challenge
The Kimi K3 model, with 2.8 trillion total parameters and approximately 104 billion active parameters per token, presents significant deployment challenges beyond its sheer size. Its architecture incorporates a mixture-…
-
Open-weights video model and Kimi K3 performance benchmarks released
ComfyUI has released an open-weights, omni-modal video model that supports 2K video output and true stereo sound, optimized for local use on GPUs like the RTX 6000 and even a 3060. Separately, a team has achieved high p…
-
AMD MI355X challenges NVIDIA, ByteDance launches Seedance 2.5 video model
AMD's MI355X processor has demonstrated superior performance over NVIDIA's offerings in Kimi K3 inference costs. Concurrently, ByteDance has unveiled its new Seedance 2.5 video generation model, which shows significant …
-
AMD MI355X GPUs offer better performance per dollar for Kimi K3 model
A blog post from Wafer.ai details how they achieved better performance per dollar by running the Kimi K3 model on AMD's MI355X GPUs. Despite Kimi K3's massive 2.8T parameter size requiring significant VRAM, the MI355X, …
-
AMD MI355X vLLM performance beats Nvidia B200 on Kimi K2.5 model
AMD's MI355X graphics card has demonstrated superior performance over Nvidia's B200 in vLLM benchmarks for the Kimi K2.5 model, a significant achievement driven by community-developed kernels. This advancement stems fro…
-
AMD MI355X performance boosted by community hackathon, rivals B200 on Kimi models · 6 sources tracked
AMD, in collaboration with GPU_MODE, has launched a $1.1 million kernel hackathon that has significantly improved the performance of its MI355X graphics card. The Readonflow Team's optimizations, focusing on MoE kernels…
-
AMD invests $5B in Anthropic for 2GW of AI GPUs, challenging Nvidia
AMD has announced a significant strategic partnership with Anthropic, involving an investment of up to $5 billion. In return, Anthropic will deploy 2 gigawatts of AMD's MI450 GPUs, starting in the first half of 2027, to…
-
Kimi K3 2.8T model requires advanced hardware beyond NVIDIA DGX B200
The Kimi K3 2.8T model is exceptionally large, requiring specialized hardware beyond a single NVIDIA DGX B200 system. To accommodate its size, configurations involving GB300 NVL72, B300, or MI355X systems are necessary …
-
Meituan releases open-source LongCat-2.0 with 1M context window
LongCat-2.0, an open-source model from Meituan, has been released under the MIT license. This model boasts 1.6 trillion parameters with approximately 48 billion active parameters and supports a 1 million token context w…
-
DeepSeekV4 shows rapid performance gains, challenging top AI models
DeepSeekV4, a 1.6 trillion parameter model, has shown significant performance gains in the 43 days since its release. Early benchmarks indicate it is competitive with or surpasses established models like GPT-4 and Claud…
-
AMD invests $3.6M in AI dev clusters to boost ROCm ecosystem
AMD is making significant efforts to support the open-source AI community, particularly with its ROCm software stack. The company has recently provided access to interconnected MI355X development clusters, valued at $3.…
-
SGLang's MI355x boosts DeepSeekv4 Pro throughput over 10x per GPU
DeepSeekv4 Pro has seen a significant performance increase, achieving over tenfold improvement in throughput per GPU. This advancement was realized through the integration of MI355x on the SGLang framework. The gains re…