-
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
[Feature] Apply structured output sampling after reasoning steps in Reasoning models
#4055
opened Mar 4, 2025 by
xihuai18
2 tasks
NVIDIA L40*8 docker NCCL Hanging During Initialization on Single Node with Multiple GPUs
#4054
opened Mar 4, 2025 by
guoshiyin-666
5 tasks done
[Bug] Directly importing Grafana JSON does not work
#4050
opened Mar 4, 2025 by
kebe7jun
5 tasks done
[Error]Input length (160062 tokens) exceeds the maximum allowed length (59862 tokens).
deepseek
help wanted
Extra attention is needed
#4048
opened Mar 4, 2025 by
tingjun-cs
[Bug] ImportError: cannot import name 'BaseImageProcessor' from 'transformers'
#4047
opened Mar 4, 2025 by
wavelet2008
5 tasks done
[Bug] Config file not found when use NVIDIA_H20-3e
quant
LLM Quantization
#4028
opened Mar 3, 2025 by
wangxiaoyang-dev
2 of 5 tasks
[Bug] How to add chat_template on Offline Batch Inference
#4024
opened Mar 3, 2025 by
oasis-0927
2 tasks done
[Bug] running requests low
deepseek
help wanted
Extra attention is needed
#4022
opened Mar 3, 2025 by
luhairong11
5 tasks done
[Bug] After using H200*8 to deploy DeepSeekR1, the large stress test model crashes
deepseek
help wanted
Extra attention is needed
#4020
opened Mar 3, 2025 by
wangguo1230
5 tasks done
[Bug] KeyError: 'model.layers.0.mlp.down_proj.weight_scale_inv' when run deepseek 671b with 64 RTX 4090 GPU
deepseek
help wanted
Extra attention is needed
#4018
opened Mar 3, 2025 by
RockGo
5 tasks done
[Bug] Qwen2.5-32B-Instruct-GPTQ-Int answer end abnormally,Qwen2.5-32B-Instruct answer is ok,use vllm is ok
#4013
opened Mar 3, 2025 by
Flynn-Zh
3 of 5 tasks
[Bug] Stuck at CUDA graph capture when serving with two A100*8 nodes
deepseek
#4007
opened Mar 3, 2025 by
Grey4sh
5 tasks done
[Feature] i can not use function call of deepseek-v3、R1 with sglang==0.4.3.post2.
#4004
opened Mar 3, 2025 by
hwaking
2 tasks
[Bug] HiCacheController Stuck when testing using multi long text documents
#3998
opened Mar 2, 2025 by
rzwei
1 of 5 tasks
[Bug] [DeepSeek-R1/V3] The description of --kv-cache-dtype in the documentation and the code is inconsistent.
#3995
opened Mar 2, 2025 by
VegetaPn
5 tasks done
[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
[Feature] Prefill assistant response
feature
good first issue
Good for newcomers
help wanted
Extra attention is needed
#3971
opened Feb 28, 2025 by
RealWorga
2 tasks done
Previous Next
ProTip!
Follow long discussions with comments:>50.