Community User
Poland
Poland
Displaying 1 to 9 of 9 repositories
Ollama v0.33.3 / MI50 (gfx906), ROCm 7.2, MTP (multi-token prediction) supported.
14d
7.4K
3
Qwen 3.5 35B A3B Q6_K ~33.4 tokens/s , ROCm Stack: 7.2.0 (Runtime + HIP) , rocBLAS 5.2.0
7m
10K+
Ollama 0.15.4 + ROCm 7.1 user-space, Tensile libs gfx906 for AMD Radeon Instinct MI50 32 GB
8m
1.6K
3
High-performance CUDA RPC Node for Hybrid LLM Clusters. Aggregates VRAM with AMD nodes.
8m
1.3K
Optimized RPC Node for AMD MI50 (gfx906) & ROCm 7.1. Part of xxDoman Hybrid Cluster.
8m
1.1K