Unverified50% confidenceFactExact time
间接绘制允许将DrawCall参数存储在GPU缓冲区中，CPU只需发起一次vkCmdDrawIndirectCount调用，配合描述符堆使渲染循环的CPU参与度趋近于零
1
Sources
50%
Confidence
Long-term
Relevance
7/7/2026
First Seen
Sources
Related Claims
UnverifiedCPU+GPU hybrid inference uses a layer-level offloading mechanism, controlling the number of offloaded layers via the n_gpu_layers parameter; the main bottleneck is PCIe bandwidth latency, which typically reduces generation speed to 1/3 to 1/2 of pure GPU inference.77% similarUnverified采用流水线架构使GPU对第N+1帧推理时CPU同时对第N帧后处理，可使理论吞吐量取决于最慢阶段而非所有阶段时间总和70% similarVerifiedllama.cpp supports hybrid CPU and GPU inference (layer offloading), allowing partial model layers to be loaded into GPU VRAM while the remaining layers are kept in memory70% similarUnverified架构被裁剪以使每次推理时被激活的参数能够恰好放进CPU的L3缓存中69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/185423API
curl https://kongchang.com/api/v1/knowledge/claims/185423MCP
get_claim(id=185423)