feifeibear / DPSKV3MFULinks
Estimate MFU for DeepSeekV3
☆24Updated 7 months ago
Alternatives and similar repositories for DPSKV3MFU
Users that are interested in DPSKV3MFU are comparing it to the libraries listed below
Sorting:
- ☆61Updated 4 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆110Updated 2 months ago
- 16-fold memory access reduction with nearly no loss☆104Updated 5 months ago
- A simple calculation for LLM MFU.☆43Updated 5 months ago
- ☆123Updated 2 months ago
- ☆50Updated 3 months ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆97Updated this week
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆133Updated 3 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆43Updated last month
- ☆38Updated 2 weeks ago
- Best practices for training DeepSeek, Mixtral, Qwen and other MoE models using Megatron Core.☆56Updated last week
- DeeperGEMM: crazy optimized version☆71Updated 3 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆47Updated last year
- ☆54Updated last year
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆59Updated last year
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆24Updated 10 months ago
- ☆43Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆107Updated 4 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆76Updated last year
- TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators☆74Updated 2 months ago
- Utility scripts for PyTorch (e.g. Memory profiler that understands more low-level allocations such as NCCL)☆49Updated 2 weeks ago
- Sequence-level 1F1B schedule for LLMs.☆17Updated last year
- An experimental communicating attention kernel based on DeepEP.☆34Updated 3 weeks ago
- Triton-based Symmetric Memory operators and examples☆23Updated this week
- ☆78Updated 4 months ago
- ☆41Updated 3 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]☆48Updated last month
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆125Updated 8 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆57Updated 9 months ago