ROCmFPX
PulseAugur coverage of ROCmFPX — every cluster mentioning ROCmFPX across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
AI developments on Mastodon: ROCmFPX code and Qwen3.8-27B release
Two separate AI-related posts are circulating on Mastodon. One developer is working on a specific code for ROCmFPX that will function exclusively on Strix Halo. Another post highlights an uncensored version of Qwen3.8-2…
-
Qwen 3.8 27B NVFP4 powers Synth Invaders on AMD hardware
A user has successfully run the Synth Invaders application, which was created using Qwen 3.8 27B NVFP4, on an AMD R9700 AI Pro with ROCmFPX. ROCmFPX is noted for providing excellent NVFP4 GGUF inference capabilities.
-
DeepSeek V4 Flash model optimized for AMD Ryzen AI MAX+ 395
A new method called ROCmFPX has been developed to fit the 284 billion parameter DeepSeek V4 Flash model into 128 GB of unified memory on an AMD Ryzen AI MAX+ 395 processor. This technique utilizes a family of block form…
-
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…