feifeibear / LLMRooflineLinks
Compare different hardware platforms via the Roofline Model for LLM inference tasks.
☆100Updated last year
Alternatives and similar repositories for LLMRoofline
Users that are interested in LLMRoofline are comparing it to the libraries listed below
Sorting:
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆87Updated last month
- ☆86Updated 2 months ago
- ☆141Updated 3 months ago
- ☆96Updated 9 months ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆55Updated 10 months ago
- ☆127Updated 5 months ago
- ☆77Updated 2 months ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆53Updated last week
- High performance Transformer implementation in C++.☆125Updated 5 months ago
- ATC23 AE☆45Updated 2 years ago
- ☆139Updated last year
- Sequence-level 1F1B schedule for LLMs.☆27Updated 3 weeks ago
- ☆60Updated last month
- DeepSeek-V3/R1 inference performance simulator☆148Updated 2 months ago
- Summary of system papers/frameworks/codes/tools on training or serving large model☆57Updated last year
- ☆14Updated this week
- A lightweight design for computation-communication overlap.☆141Updated last week
- Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang☆53Updated 7 months ago
- Fast and memory-efficient exact attention☆74Updated this week
- ☆148Updated 5 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆79Updated last month
- Standalone Flash Attention v2 kernel without libtorch dependency☆110Updated 9 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆38Updated last week
- Stateful LLM Serving☆73Updated 3 months ago
- Pipeline Parallelism Emulation and Visualization☆42Updated last week
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆92Updated 3 weeks ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆163Updated 9 months ago
- PyTorch distributed training acceleration framework☆49Updated 4 months ago
- Implement Flash Attention using Cute.☆87Updated 6 months ago
- DeeperGEMM: crazy optimized version☆69Updated last month