feifeibear / LLMRooflineLinks
Compare different hardware platforms via the Roofline Model for LLM inference tasks.
☆120Updated last year
Alternatives and similar repositories for LLMRoofline
Users that are interested in LLMRoofline are comparing it to the libraries listed below
Sorting:
- ☆155Updated 11 months ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆123Updated last month
- ☆105Updated last year
- ☆96Updated 10 months ago
- Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend☆107Updated this week
- High performance Transformer implementation in C++.☆150Updated last year
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆92Updated 2 weeks ago
- A lightweight design for computation-communication overlap.☆219Updated 3 weeks ago
- ☆130Updated last year
- Stateful LLM Serving☆95Updated 10 months ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆101Updated last month
- ☆85Updated 9 months ago
- LLM training technologies developed by kwai☆70Updated 2 weeks ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆161Updated 4 months ago
- Fast and memory-efficient exact attention☆111Updated last week
- ☆47Updated last year
- PyTorch distributed training acceleration framework☆55Updated 5 months ago
- llm theoretical performance analysis tools and support params, flops, memory and latency analysis.☆115Updated 6 months ago
- Summary of the Specs of Commonly Used GPUs for Training and Inference of LLM☆75Updated 5 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆233Updated 2 years ago
- ☆65Updated 9 months ago
- FlagCX is a scalable and adaptive cross-chip communication library.☆172Updated this week
- Accepted to MLSys 2026☆70Updated last week
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆96Updated 4 months ago
- gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling☆53Updated 3 weeks ago
- ☆152Updated last year
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆92Updated 3 weeks ago
- DeepSeek-V3/R1 inference performance simulator☆176Updated 10 months ago
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆283Updated 11 months ago
- ☆141Updated last year