Skip to content

Issues: deepseek-ai/DeepSeek-V2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

29 Open 11 Closed
29 Open 11 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

缓存C<sup>KV</sup><sub>t</sub> 多卡并行推理是否需要每张卡缓存一份
#41 opened May 20, 2024 by c-dafan
How to fine-tune deepseek v2 models?
#40 opened May 19, 2024 by satheeshkatipomu
发送图片
#39 opened May 19, 2024 by 21JayChou
请增加gguf支持
#38 opened May 19, 2024 by jackbapa
服务器部署问题
#37 opened May 17, 2024 by airsxue
1
太容易陷入死循环了
#36 opened May 17, 2024 by rak-bn
如何能达到论文里说的吞吐量50000多tokens
#35 opened May 17, 2024 by ly19970621
2
Invalid max_token values
#34 opened May 16, 2024 by audreyeternal
无法支持 autogpt 中的 langchain
#33 opened May 16, 2024 by chenny
'detail': 'Content Exists Risk'
#32 opened May 16, 2024 by 18534516725
1
偏好数据构造方法
#31 opened May 15, 2024 by pandaupc
BadRequestError: Error code: 400 - {'detail': 'Content Exists Risk'}
#30 opened May 15, 2024 by judeomg
3
当结尾 "finish_reason":"stop" 时，role 值为空
#29 opened May 15, 2024 by yttchan
Add MoE offloading strategy？
#28 opened May 15, 2024 by Minami-su
Comparison Between MLA and MHA in dense model
#26 opened May 13, 2024 by mx8435
why i use vllm inference deepseek v2 ,speed is low
#24 opened May 12, 2024 by ZzzybEric
Reproduce inference benchmark mentioned in the paper
#21 opened May 11, 2024 by zhouheyun
2
Error executing method determine_num_available_blocks
#20 opened May 10, 2024 by empty2enrich
MLA vs MHA
#19 opened May 10, 2024 by jiangix-paper
量化
#15 opened May 9, 2024 by ccp123456789
1
请扩充模型的中文词表
#14 opened May 9, 2024 by sohowj
1
Clarifications Needed on KVCache Compression and Matrix Operations in MLA KVCache
#10 opened May 8, 2024 by hxer7963
1
源码
#8 opened May 8, 2024 by yyfyyf123
1
How to deploy in VLLM?
#7 opened May 7, 2024 by ZHENG518
9
V-MoE token droping and MoD
#5 opened May 7, 2024 by liyucheng09
1
ProTip! Follow long discussions with comments:>50.