Skip to content

Issues: EmbeddedLLM/vllm

Beta
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

26 Open 22 Closed
26 Open 22 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

[Bug]: Fix the triton chunked prefill decode V1 bug bug Something isn't working
#63 opened May 14, 2025 by tjtanaa
2 tasks done
@kliuae
[Feature]: Integrate AITER MLA V1 from Upstream enhancement New feature or request
#62 opened May 14, 2025 by tjtanaa
1 task done
[Feature]: MTP on ROCm enhancement New feature or request
#61 opened May 13, 2025 by tjtanaa
1 task done
[Feature]: AITER Grouped TopK v1
#60 opened May 13, 2025 by vllmellm
1 task done
[Feature]: Move to use AITER v0.1.1 enhancement New feature or request
#58 opened May 7, 2025 by tjtanaa
1 task done
[Feature]: [Feature]: Optimize DeepSeek V3 for V1 Engine enhancement New feature or request
#57 opened May 7, 2025 by tjtanaa
1 task done
[Usage]: Check if lmcache works on ROCm question Further information is requested
#56 opened May 7, 2025 by tjtanaa
1 task done
[Usage]: Document how to use AITER on vLLM documentation Improvements or additions to documentation
#55 opened May 7, 2025 by tjtanaa
1 task done
[Usage]: PD-disaggregated Inferencing question Further information is requested
#54 opened May 7, 2025 by tjtanaa
1 task done
[Bug]: direct_register_custom_ops incur overhead bug Something isn't working
#52 opened May 6, 2025 by tjtanaa
1 task done
2
[Bug]: Qwen 2.5 72B TPOT regression bug Something isn't working
#51 opened Apr 30, 2025 by tjtanaa
1 task done
[Bug]: Regression in DeepSeekV3 by 20% bug Something isn't working
#50 opened Apr 30, 2025 by tjtanaa
1 task done
2
[Feature]: Check if the moe_2stage is compatible with no-EP and EP of Qwen3 MoE FP8 model enhancement New feature or request
#49 opened Apr 30, 2025 by tjtanaa
1 task done
[Bug]: Benchmark MoE tuning script bug on ROCM bug Something isn't working
#48 opened Apr 30, 2025 by tjtanaa
1 task done
[Feature]: CK MoE 2 stage enhancement New feature or request
#47 opened Apr 30, 2025 by tjtanaa
1 task done
2
[Feature]: Enable MLA for V1 on AMD [Triton MLA] enhancement New feature or request
#46 opened Apr 23, 2025 by tjtanaa
1 task done
@vllmellm
[RFC]: All Ops should be determined during init and wrapped in a Layer Module to avoid envs.ENVIRON overhead enhancement New feature or request help wanted Extra attention is needed
#45 opened Apr 22, 2025 by tjtanaa
1 task done
@vllmellm
1
[Bug]: Bugfix LoRA for ROCm due to incompatible triton arguments are passed. bug Something isn't working
#42 opened Apr 17, 2025 by tjtanaa
1 task done
@tjtanaa
1
[Bug]: Bugfix AITER RMSNORM bug Something isn't working
#39 opened Apr 16, 2025 by tjtanaa
1 task done
AITER INT8 a8w8 GEMM kernel() for V1 Engine
#35 opened Apr 16, 2025 by vllmellm
AITER Paged Attention() for V1 Engine
#34 opened Apr 16, 2025 by vllmellm
@vllmellm
AITER Block Scaled A8W8 GEMM() for V1 Engine enhancement New feature or request
#33 opened Apr 16, 2025 by vllmellm
@tjtanaa @vllmellm
1
AITER RMS Norm for V1 Engine()
#31 opened Apr 16, 2025 by vllmellm
Enable AITER Linear() for V1 Engine enhancement New feature or request
#30 opened Apr 16, 2025 by vllmellm
@tjtanaa
3
[Feature]: Roadmap for 2nd Quarter 2025 enhancement New feature or request
#29 opened Apr 15, 2025 by tjtanaa
1 of 5 tasks
ProTip! What’s not been updated in a month: updated:<2025-04-25.