issues Search Results · repo:deepseek-ai/DeepSeek-V3 language:Python
Filter by
581 results
(169 ms)581 results
indeepseek-ai/DeepSeek-V3 (press backspace or delete to remove)Describe the bug A clear and concise description of what the bug is.
To Reproduce Steps to reproduce the behavior.
Expected behavior A clear and concise description of what you expected to happen.
Screenshots ...
Jorodimitrov85
- Opened 3 days ago
- #950
Currently, DeepSeek models treat each conversation turn as an independent request, relying solely on the provided
context. In long-running sessions, this forces users to repeatedly send large portions ...
Pomsakar
- Opened 4 days ago
- #949
Describe the bug A clear and concise description of what the bug is.
To Reproduce Steps to reproduce the behavior.
Expected behavior A clear and concise description of what you expected to happen.
Screenshots ...
aa4544142-cyber
- Opened 12 days ago
- #947
Describe the bug I need to use the DeepSeek model in projects like Claude Code Proxy and Claude Code Router to utilize
their tool call functionality. The APIs I purchased from the official website are ...
adogwangwang
- 1
- Opened 16 days ago
- #944
NB: ALL THE FINDINGS ARE IN THE PDF ATTACHED AT THE END
Dear DeepSeek Support Team,
I am Thierry Nshimiyumukiza, an independent security researcher, and I have identified multiple critical vulnerabilities ...
thierrynshimiyumukiza
- 1
- Opened 17 days ago
- #943
Describe the bug To add the value from two experts, we should use torch.scatter_reduce(..., reduce= sum ). But the code
here
https://github.com/deepseek-ai/DeepSeek-V3/blob/f6e34dd26772dd4a216be94a8899276c5dca9e43/inference/model.py#L686C13-L686C63 ...
yaoshiang
- Opened 17 days ago
- #942
img width= 1879 height= 261 alt= Image src=
https://github.com/user-attachments/assets/0f1e71a0-46b9-45c1-8f1a-9d5648eb9638 /
Irignabin
- 1
- Opened 19 days ago
- #939
Describe the bug Hi team, I m working on reproducing the great deepseek-v3 model on torchtitan . While I m trying to run
numerical verification, I noticed the rotary embedding in HF and this repo is different. ...
wwwjn
- 1
- Opened 19 days ago
- #938
给到cpu和gpu两份代码,让模型进行代码比对并修改cuda代码中的问题,模型趋向于摆烂,原封不动输出原始错误的代码。思考时间远长于kimi和openai,但是都没有给出实际有效的解决方案,可见就目前cuda代码的训练数据所有大模型都挺缺的,这边可以提供相关的cpu和cuda代码
mcmingchang
- 2
- Opened 22 days ago
- #937
Revisa mi documento si cumple ya con lo que
EM_M7_A1_ARISVET_ARACELI_JAIMES_ESTRADA.docx
04_em_07_emcved_UDA1_S2_material_de_estudio (1).pdf
04_em_07_emcved_semana_1.pdf
se pide
aracelijaimese
- Opened 23 days ago
- #936

Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Press the /
key to activate the search input again and adjust your query.
Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Press the /
key to activate the search input again and adjust your query.