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

68 Open 23 Closed
68 Open 23 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
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

deepseek v2.5 w4a16在vllm-0.6.3.post1运行失败
#99 opened Dec 9, 2024 by cxmt-ai-tc
1
登录界面有bug
#98 opened Dec 2, 2024 by huhe2018
不能在cursor编辑器上用自定义api是吗？
#97 opened Nov 15, 2024 by PeyFon
2
一个账户创建了五十个api，但一个api没问题，但多了会报错 处理时发生未知错误: Connection error
#96 opened Oct 30, 2024 by wanglu2014
Access to Deepseek chat is blocked for no reason.
#95 opened Oct 29, 2024 by Farooq87
1
default temperature of this model
#94 opened Oct 27, 2024 by ssk705
NAN issue using FP16 to load the model
#93 opened Oct 25, 2024 by zitgit
Inquiry about Key/Value Storage and Matrix Merging in DeepSeekerV2 Inference Code
#92 opened Sep 26, 2024 by xlim1996
Function Calling比以前难触发了
#88 opened Sep 8, 2024 by whoisfucker
9
Exploring the Combined Effects of YaRN and Adjusted rope_base Values in deepseek v2
#87 opened Sep 4, 2024 by hannlp
Question about the design of bos and eos token
#85 opened Aug 28, 2024 by jojo23333
线上api如何稳定的触发 tool_calls
#84 opened Aug 26, 2024 by wssnail
4
ValueError: The model's max seq len (163840) is larger than the maximum number of tokens that can be stored in KV cache (13360). Try increasing gpu_memory_utilization or decreasing max_model_len when initializing the engine.
#83 opened Aug 15, 2024 by ArtificialZeng
3
empty response from server
#82 opened Aug 12, 2024 by 879611427
2
HuggingFace中开源的代码似乎没有实现矩阵合并
#80 opened Aug 6, 2024 by meteorlin
1
多轮在训练中是否需要特殊间隔符，用什么间隔符号？
#79 opened Aug 4, 2024 by AceCHQ
DeepSeek-V2-Lite-Chat模型启动依赖问题
#78 opened Aug 2, 2024 by Malowking
1
自配大模型服务器如何选择GPU，CPU和内存
#77 opened Jul 31, 2024 by zhanghanting
Error executing method determine_num_available_blocks: vLLM multi node fails for both DeepSeek-Coder-V2-Instruct and DeepSeek-Coder-V2-Lite-Instruct
#76 opened Jul 28, 2024 by liangfang
1
0628版本加载报错
#75 opened Jul 26, 2024 by bestpredicts
为何我在A800上运行DeepSeek-V2-Lite-Chat (SFT)，竟然消耗60G的显存？！
#74 opened Jul 19, 2024 by juhengzhe
3
about the active param counts of DeepSeek-V2-Lite
#73 opened Jul 18, 2024 by imhmhm
Why max_model_len only 8192 when inferencing with vLLM for DeepSeek-V2-Chat?
#72 opened Jul 18, 2024 by ybdesire
怎么用dspy里的方法来调用deepseek？
#71 opened Jul 16, 2024 by buchikeke
2
What's the Prompt and Response length in the Paper?
#70 opened Jul 9, 2024 by JadeRay
ProTip! Add no:assignee to see everything that’s not assigned.