alibaba / InferSim
A Lightweight LLM Inference Performance Simulator
Why this job: says: llm inference; topics: llm-inference
What it does
- Attention. MHA/GQA, MLA. Benchmarked on FlashInfer, FlashAttention-3, FlashMLA.
- MoE. GroupedGEMM. Benchmarked on DeepGEMM.
- Linear. GEMM. Benchmarked on DeepGEMM.
- Parallelization. DP Attn, EP MoE.
- Large EP. DeepEP dispatch and combine, with normal and low_latency mode.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 21 days ago
- Stars
- 103
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 96% of the code
Is it looked after?
- Contributors
- 3
- Last 90 days
- Issues
- 17% closed
- 5 still open
- Pull requests
- 9 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| vllm-project / vllm | 96,588 | today | Apache-2.0 | Mac, Linux |
| HMDSimDev / heartmorrow | 185 | 3 months ago | Unlicense | No downloads |
| pegainfer-project / pegainfer | 738 | yesterday | Apache-2.0 | Linux |
More: languages, topics and project record
Languages
- Python 96%
- Shell 4%
Topics
- deepseek
- llm
- llm-inference
- qwen3
- simulator
Project record
- JobLocal LLMs
- StatusListed
- Commits55
- Forks31
- Watching0
- Stars in 28 days0
- CreatedSep 28, 2025
- First seen by usNov 7, 2026
- CheckedNov 7, 2026