mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2026-11-05 01:07:28 +00:00
[GH-ISSUE #1497] 为什么双卡推理的表现和单卡差不多?能够进行优化调整吗? #1000
Labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
kvcache-ai/ktransformers#1000
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @corengh on GitHub (Sep 8, 2025).
Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/1497
CPU:INTEL XEON PLATINUM 8582C 2.6GHZ 60核
内存:DDR5-5600 32G × 8
显卡:NVIDIA GeForce RTX 3090 24G × 2
系统:Ubuntu 24.04
KTranformers 版本:0.3.2
加载模型:DeepSeek-R1-UD-IQ1_S(140.23G)
使用
DeepSeek-V3-Chat.yaml进行单卡推理,单卡显存占用大概 12G 左右;使用DeepSeek-V3-Chat-multi-gpu.yaml进行双卡推理时,显存占用大概是 6.2G + 6.5G 。但是两者在性能表现上并没有体现出差异,decode 都是 13.7 Tokens/s 左右。求解的疑惑是:
@corengh commented on GitHub (Sep 9, 2025):
multi-gpu 似乎确实无法提高性能表现
Ktransformers FAQ