mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2026-11-05 01:07:28 +00:00
[GH-ISSUE #1187] [Feature] 能否在readme 里面添加一下 单独cpu 版本的编译和 带cuda版本的编译指导 #814
Labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
kvcache-ai/ktransformers#814
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 @luotf89 on GitHub (Apr 23, 2025).
Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/1187
检查清单
需求背景
能否在readme 里面添加一下 单独cpu 版本的编译和 带cuda版本的编译指导
相关资源
No response
@yeungtuzi commented on GitHub (Apr 23, 2025):
纯CPU版本建议直接使用vLLM vLLM,vLLM更成熟。
@qiyuxinlin commented on GitHub (Apr 24, 2025):
@luotf89 您好,默认是 cuda 版本的编译指导,单独 cpu 版本 balance_serve 后端缺少 attention、rms、linear 算子,后续可能支持纯 cpu 运行
@spaceater commented on GitHub (Apr 29, 2025):
vLLM(0.8.4)在CPU平台不支持MoE模型的awq、gptq量化,因为MoE模型使用的是marlin内核,而marlin内核不支持CPU。