-
Notifications
You must be signed in to change notification settings - Fork 1.1k
Issues: sgl-project/sglang
[Feature] Optimizing DeepSeek with the DeepSeek Infra OSS com...
#3758
opened Feb 21, 2025 by
zhyncs
Open
3
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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
[Bug] Distributed Initialization of SGLang with accelerate launch
#3974
opened Mar 1, 2025 by
jhinpan
5 tasks done
[Feature] Support model unsloth/DeepSeek-R1-GGUF
deepseek
#3973
opened Mar 1, 2025 by
Qiaolin-Yu
2 tasks done
DeepSeek-R1 Optimization Options Ablations
deepseek
high priority
speculative-decoding
#3956
opened Feb 28, 2025 by
m0g1cian
[Bug] RecursionError: maximum recursion depth exceeded while calling a Python object
#3953
opened Feb 28, 2025 by
Hiwyl
5 tasks done
how to fix "CUDA_HOME environment variable is not set" in docker
#3952
opened Feb 28, 2025 by
Flynn-Zh
[Bug] After using --enable-torch-compile, garbled output
#3944
opened Feb 28, 2025 by
echozyr2001
5 tasks done
[Bug] DeepSeek R1/V3 error when enable dp-attention and speculative-algo NEXTN
#3943
opened Feb 28, 2025 by
TianQiLin666666
5 tasks done
Why are there a group of processes concentrated on a single GPU?
high priority
#3942
opened Feb 28, 2025 by
WalterYOO
[Bug] pytest shouldn't be required in production
#3938
opened Feb 28, 2025 by
KCFindstr
5 tasks done
[Bug] KeyError: 'model.layers.0.self_attn.k_scale'
#3936
opened Feb 27, 2025 by
Swipe4057
5 tasks done
sglang serving crashes with torch profiler enabled
#3931
opened Feb 27, 2025 by
dulvqingyun
2 of 5 tasks
[Question] Why is the performance worse after --enable-flashinfer-mla on H20
#3917
opened Feb 27, 2025 by
tianchongchong
[Bug] OpenAI compatible api return finish_reason as empty string instead of null causing json deseriliazition failure
#3912
opened Feb 27, 2025 by
jzhouw
5 tasks done
[Bug] Server crash when Input length exceeds the maximum allowed length
#3910
opened Feb 27, 2025 by
YangZeyu95
2 of 5 tasks
[Question] Optimization Options for DeepSeek-r1 Implementation
#3906
opened Feb 27, 2025 by
JiangLiNSCC
[Question] three questions about fused MoE Gemm implementation
#3904
opened Feb 27, 2025 by
danielhua23
[Feature] Allow Serving Requests During CUDA Graph Capture
feature
good first issue
Good for newcomers
#3902
opened Feb 27, 2025 by
junliu-mde
2 tasks done
[Bug] OpenAI Endpoint '/v1/batches':
error: Object of type ChoiceLogprobs is not JSON serializable
#3895
opened Feb 26, 2025 by
dcfidalgo
5 tasks done
[Bug] Dimension mismatched error when capturing cuda graph while enabling NEXTN
#3891
opened Feb 26, 2025 by
TangChangcheng
5 tasks done
Previous Next
ProTip!
Adding no:label will show everything without a label.