-
Notifications
You must be signed in to change notification settings - Fork 1.2k
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] sglang offline inference: "cuda out of memory" error, while vllm works fine
#4248
opened Mar 10, 2025 by
xhd0728
5 tasks done
[Bug] Enable --enable-flashinfer-mla, the result has high rate to output duplicated words/sentence.
#4246
opened Mar 10, 2025 by
anyshu
1 of 5 tasks
[Bug] vllm vs sglang performance test comparison
#4245
opened Mar 10, 2025 by
luhairong11
5 tasks done
[Feature] sglang:gen_throughput metrics still have value when there have no request to SGLang server
#4244
opened Mar 10, 2025 by
b02330224
2 tasks
[Bug] SGLang QwQ Tool use with LibreChat agent fails
#4236
opened Mar 9, 2025 by
JohnZolton
1 of 5 tasks
[Bug] ImportError AWQMoEMethod from 'vllm.model_executor.layers.quantization.awq_marlin' after launch_server in all_xpu build
#4234
opened Mar 9, 2025 by
sairampillai
4 of 5 tasks
[Bug] The memory capacity is unbalanced. Some GPUs may be occupied by other processes.
#4233
opened Mar 9, 2025 by
inkhare
1 of 5 tasks
[Feature] A simpler way for updating weight of VerlEngine
#4227
opened Mar 9, 2025 by
yitianlian
2 tasks done
[Feature] SGLang Support for TileLang
help wanted
Extra attention is needed
high priority
#4221
opened Mar 9, 2025 by
Cunxiao2002
[Feature] sglang-router should perform extra status check on workers upon startup in addition to port reachability
#4208
opened Mar 8, 2025 by
junliu-mde
2 tasks done
[Bug] I encountered a 'Capture CUDA graph failed' error.
#4205
opened Mar 8, 2025 by
inkhare
1 of 5 tasks
[Bug] After enabling flashinfer-mla for DeepSeek R1, I observed no throughput performance improvement.
deepseek
#4204
opened Mar 8, 2025 by
inkhare
2 of 5 tasks
[Bug] text generation hangs after serving some requests
#4191
opened Mar 8, 2025 by
RenaultAI
5 tasks done
Our performance test of DeepSeek-R1-Block-INT8 is inconsistent with #3730
#4180
opened Mar 7, 2025 by
itechbear
[Feature] Support correctly exit using ctrl+c
feature
#4173
opened Mar 7, 2025 by
RenfeiChen96
2 tasks done
[Bug] Qwen2.5-VL-7B-Instruct Inference Server crashes
visIon-LM
#4171
opened Mar 7, 2025 by
felmoreno1726
5 tasks done
[Bug] DeepSeek server crushed while using sglang.bench_serving
#4161
opened Mar 7, 2025 by
sunzx8
3 of 5 tasks
[Bug] sglang-router failure when first load model, try again successed
router
#4160
opened Mar 7, 2025 by
Kelatte
5 tasks done
[Bug] Key conflict of
AutoImageProcessor.register
visIon-LM
#4159
opened Mar 7, 2025 by
SpinoPi
5 tasks done
[Bug] Accuracy issue with SGLang using DeepSeek-R1-AWQ
quant
LLM Quantization
#4158
opened Mar 7, 2025 by
TheTinyTeddy
5 tasks done
[Bug] Incorrect DP rank and DP worker messaging when using TP > 1 and DP > 1
#4149
opened Mar 6, 2025 by
wangray
5 tasks done
[Bug] Is YaRN supported in SGLang? How to enable it?
#4145
opened Mar 6, 2025 by
boqianzee
5 tasks done
Previous Next
ProTip!
no:milestone will show everything without a milestone.