CalvinXKY / mfu_calculationLinks
A simple calculation for LLM MFU.
☆43Updated 5 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:
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆97Updated this week
- ☆78Updated 4 months ago
- Utility scripts for PyTorch (e.g. Memory profiler that understands more low-level allocations such as NCCL)☆44Updated 2 weeks ago
- ☆146Updated 5 months ago
- ☆61Updated 4 months ago
- GPTQ inference TVM kernel☆40Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆107Updated 4 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆137Updated last month
- ☆92Updated 5 months ago
- DeeperGEMM: crazy optimized version☆71Updated 3 months ago
- Estimate MFU for DeepSeekV3☆24Updated 7 months ago
- ☆50Updated 3 months ago
- An experimental communicating attention kernel based on DeepEP.☆34Updated 3 weeks ago
- ☆54Updated last year
- ☆85Updated 3 years ago
- PyTorch bindings for CUTLASS grouped GEMM.☆110Updated 2 months ago
- ☆43Updated last year
- ☆97Updated 11 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆76Updated last year
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆57Updated 9 months ago
- Summary of system papers/frameworks/codes/tools on training or serving large model☆57Updated last year
- Toolchain built around the Megatron-LM for Distributed Training☆58Updated 2 weeks ago
- ☆38Updated 2 weeks ago
- 16-fold memory access reduction with nearly no loss☆104Updated 5 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆111Updated last year
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆59Updated last year
- A lightweight design for computation-communication overlap.☆157Updated last week
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆79Updated 9 months ago
- nnScaler: Compiling DNN models for Parallel Training☆115Updated last week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆325Updated this week