Transformers adds FP8 backend for QuantizedCache
Native PyTorch FP8 concat replaces a defensive workaround, with layout fixes aimed at future kernels.
By tensor#quantization
llama.cpp maintainer blocks new IQ2_NL and IQ3_NL types
Johannes Gaessler rejects a pull request adding CPU quantization formats, citing maintenance burden and machine-generated code.
By tensorllama.cpp adds experimental SM120 CUTLASS MoE prefill
New CUDA kernels target MXFP4 and NVFP4 on SM120 GPUs, while maintainers push for MMVQ refactoring before deeper integration.
By tensor