general family · filed under inference & serving
Low-bit quantization
A broad family of quantization methods using low bit widths; no specific algorithm is identified.
Also called low-bit methods.
- source
- 1
- model
- 1
- labs adopt it
- 0
- strongest
- mentioned
How sources treat it
One count per evidence span, weakest treatment to strongest.
mentioned 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
AngelSlim covers quantization, low-bit methods, and speculative sampling.
mentionedpost trainingin AngelSlimTencent
Filed alongside
Other methods under inference & serving :: inference quantization.
FP8 KV-cache quantizationFP8FP4 KV-cache quantizationNVFP4 quantizationFour-Over-SixMXFP4 weight quantizationPost-training quantizationQuantizationBlock-scaled INT8 quantization with stochastic roundingFP8 E4M3 quantizationGGUFMax-based scalingMSE-based scalingMXFP8 activation quantizationNVFP4 KV-cache quantizationNVFP4 ModelOpt re-quantizationSSM cache quantizationAWQ INT4 weight quantization (W4A16)BF16 inferenceBlock-wise E4M3 FP8 weight quantizationChannel-wise quantizationDynamic activation scalingEmbedding and KV-cache quantizationEmpirical bits-per-element budget selection