llama.cpp Adds Tensor Merge on GGUF Conversion

Open-source project llama.cpp merged a pull request (#31028) by contributor am17an that merges tensors during conversion. The change may require users to reconvert existing GGUF model files.

• llama.cpp Adds GPU Cache for MoE Experts in Host Memory2026-10-07
• llama.cpp merges MTP support for Qwen Flash Next2026-10-01
• llama.cpp discloses out-of-bounds write flaw2026-10-26
• 8GB GPU runs 262K-context Qwen quant at 70 T/s2026-10-24
• ISTA-DASLab releases quantized DeepSeek-V4.1-Flash2026-10-24