mixed-precision quantization
- Papers
- 3
- Released code
- 0
- First seen
- Oct 2026
- Latest
- Nov 2026
3 papers in the last two months, against 0 in the two before.
Start here
Three papers to read first, in the order they came out- 1One random probe can guide data-free mixed-precision model quantization
Round-to-nearest quantization error is spectrally flat, letting one Gaussian probe estimate tensor sensitivity and allocate mixed precision without calibration data.
Oct 2026 - 2Mixed-precision LLM accelerator turns lower bit weights into proportionally faster compute
FIGFLEX's radix-4 FP-INT datapath makes LLM GEMM compute scale with weight bit-width, and its mixed-precision quantizer beats existing low-bit methods.
Oct 2026 - 3Coordinating cache precision cuts agents' memory use by a third
CoMixKV jointly allocates precision across agent KV caches under a shared memory budget, improving accuracy and memory efficiency.
Nov 2026
How fast it is moving
Often studied with
post-training quantizationQuantizing pre-trained neural network weights and activations to2 togetherkv cache compressionReducing the size of the key-value cache in transformers via selective retention, low-rank updates, or adaptive compression.1 togetherlarge language modelA neural network trained on massive text corpora to generate coherent text and perform diverse language tasks.1 togetherThe papers
Most central to this idea first, not most recent.
- Chinese Techcs.LG
Coordinating cache precision cuts agents' memory use by a third
CoMixKV jointly allocates precision across agent KV caches under a shared memory budget, improving accuracy and memory efficiency.
Xiamen University, Tencent Inc. · Nov 2026
- Academiccs.AR
Mixed-precision LLM accelerator turns lower bit weights into proportionally faster compute
FIGFLEX's radix-4 FP-INT datapath makes LLM GEMM compute scale with weight bit-width, and its mixed-precision quantizer beats existing low-bit methods.
University of California, Irvine · Oct 2026
- Industrycs.CL
One random probe can guide data-free mixed-precision model quantization
Round-to-nearest quantization error is spectrally flat, letting one Gaussian probe estimate tensor sensitivity and allocate mixed precision without calibration data.
Blacksheep ai. · Oct 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.