Home / AI Cards / 昇腾 950DT
华为昇腾

昇腾 950DT

类GPU混合 · 2026 · Datacenter

Positioning

For training and long-context decode, core of Atlas 950

标签:NPU国产FP8

Specifications

厂商
华为昇腾
架构
类GPU混合
类别
Datacenter
制程
SMIC 7nm
发布时间
2026
显存容量
144 GB
显存类型
HiZQ 2.0 自研HBM
显存带宽
4 TB/s
FP16 算力
— TFLOPS
FP8 算力
1000 TFLOPS
FP4 算力
2 PFLOPS
互联带宽
2 TB/s
功耗 TDP
— W
状态
Upcoming

Sources

数据来自厂商官方文档与公开行业报告(NVIDIA、AMD、华为、IDC 等)。算力数值请结合精度与稀疏/稠密口径阅读;本站统一标注,避免纸面参数误导。采集时间 2026-11。

Frequently Asked Questions

Clear answers about AI accelerators, specs, precision and buying. (10 questions)

What is the memory capacity of 昇腾 950DT?+
144 GB HiZQ 2.0 自研HBM with 4 TB/s bandwidth.
What is the FP16 throughput of 昇腾 950DT?+
Not disclosed TFLOPS (dense).
What is the difference between a GPU and an NPU?+
A GPU (Graphics Processing Unit) is a general-purpose parallel processor with many cores, excellent at matrix math and flexible enough for training and rendering. An NPU (Neural Processing Unit) is a specialized chip designed only for neural-network inference and training, with dataflow architectures that trade flexibility for higher efficiency. In short: GPU is general-purpose and programmable; NPU is domain-specific and more power-efficient for fixed AI workloads.
What is an AI accelerator card?+
An AI accelerator card is a PCIe or OAM add-in card that offloads machine-learning training and inference from the CPU. It typically carries a GPU, NPU or ASIC plus high-bandwidth memory (HBM) and is used in servers and workstations to run large neural networks efficiently.
What is the difference between training and inference hardware needs?+
Training needs very high compute throughput, large memory capacity and fast interconnect to scale across many GPUs. Inference prioritizes low latency, high throughput per watt, lower precision (INT8/FP8/FP4) and cost. Training cards are usually top-tier (H100/B200); inference can use mid-range or NPU/ASIC solutions.
What is HBM and how is it different from GDDR?+
HBM (High Bandwidth Memory) stacks DRAM vertically and connects via a wide 1024/2048-bit interposer, delivering far higher bandwidth and lower power than GDDR, which uses wide-but-shorter parallel buses on the PCB. AI accelerators use HBM3/HBM3e/HBM4 because large models are memory-bandwidth bound.
What does OAM mean in AI accelerator modules?+
OAM (OCP Accelerator Module) is an open hardware standard from the Open Compute Project defining the module form factor, cooling and high-speed interfaces for AI accelerators. It lets different vendors cards fit the same server baseboard, easing system integration.
Is more VRAM always better?+
Not always. Larger VRAM lets you hold bigger models and batches, but if the workload is compute-bound, extra memory adds cost without speed gains. Bandwidth often matters more than raw capacity. Match VRAM to model size plus KV-cache headroom.
What is a GPU cluster?+
A GPU cluster connects many accelerator servers with high-speed networking (InfiniBand/RoCE) so they train or serve models in parallel. Scaling out requires both fast internode networking and parallelism strategies (data, tensor, pipeline parallelism).
What do FP64, FP32, FP16, BF16, FP8 and FP4 mean?+
They are numeric precisions. FP64/FP32 are high precision for scientific/HPC work; FP16 and BF16 are half precision widely used in AI training; FP8 and FP4 are lower precisions used in inference to double throughput and cut memory. Fewer bits mean faster and smaller but lower accuracy.