Public KG record
GPTQ
Recorded overview
KG-recorded mechanism related to GPTQ; detailed English notes are not yet available.
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Integrations: GPTQModel输出可运行于Transformers
- Performance: NVIDIA A100上相对FP16端到端加速约3.25倍
- Performance: NVIDIA A6000上相对FP16端到端加速约4.5倍
- Performance: 相对FP16在NVIDIA A100上加速约3.25倍
- Performance: 相对FP16在NVIDIA A6000上加速约4.5倍
Evidence coverage
The KG currently records 8 known information dimensions and has 11 undocumented dimensions, linked to 2 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- Safetensors — uses
- 近似二阶信息 — uses