CalvinXKY / mfu_calculationLinks
A simple calculation for LLM MFU.
☆38Updated 3 months ago
Alternatives and similar repositories for mfu_calculation
Users that are interested in mfu_calculation are comparing it to the libraries listed below
Sorting:
- A lightweight design for computation-communication overlap.☆132Updated 3 weeks ago
- Estimate MFU for DeepSeekV3☆24Updated 4 months ago
- ☆59Updated last month
- ☆76Updated last month
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆79Updated 6 months ago
- GPTQ inference TVM kernel☆38Updated last year
- ☆36Updated 9 months ago
- ☆85Updated 2 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆48Updated 7 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆69Updated 11 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆83Updated last month
- ☆54Updated last year
- ☆49Updated 2 weeks ago
- Summary of system papers/frameworks/codes/tools on training or serving large model☆57Updated last year
- A minimal implementation of vllm.☆41Updated 10 months ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆50Updated 2 weeks ago
- nnScaler: Compiling DNN models for Parallel Training☆113Updated last month
- 方便扩展的Cuda算子理解和优化框架,仅用在学习使用☆15Updated 11 months ago
- DeeperGEMM: crazy optimized version☆69Updated 3 weeks ago
- ☆21Updated last month
- PyTorch bindings for CUTLASS grouped GEMM.☆125Updated 5 months ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆54Updated 10 months ago
- ☆83Updated 3 years ago
- Sequence-level 1F1B schedule for LLMs.☆17Updated last year
- ATC23 AE☆45Updated 2 years ago
- PyTorch bindings for CUTLASS grouped GEMM.☆93Updated this week
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆157Updated 8 months ago
- ☆95Updated 8 months ago
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆36Updated last month
- ☆70Updated 2 weeks ago