HabanaAI / Megatron-DeepSpeed
Intel Gaudi's Megatron DeepSpeed Large Language Models for training
☆13Updated last month
Related projects ⓘ
Alternatives and complementary repositories for Megatron-DeepSpeed
- ☆55Updated 5 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆38Updated 10 months ago
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆34Updated 8 months ago
- A Python library transfers PyTorch tensors between CPU and NVMe☆98Updated last week
- Memory Optimizations for Deep Learning (ICML 2023)☆60Updated 8 months ago
- ☆47Updated 2 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆51Updated 2 months ago
- ☆44Updated 11 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆147Updated 4 months ago
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆57Updated this week
- TensorRT LLM Benchmark Configuration☆11Updated 3 months ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆112Updated 8 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆57Updated 5 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆53Updated 3 weeks ago
- Repository for CPU Kernel Generation for LLM Inference☆25Updated last year
- Unit Scaling demo and experimentation code☆16Updated 8 months ago
- ☆88Updated 2 months ago
- Elixir: Train a Large Language Model on a Small GPU Cluster☆13Updated last year
- GPU operators for sparse tensor operations☆29Updated 8 months ago
- Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆79Updated this week
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆103Updated 3 months ago
- GPTQ inference TVM kernel☆36Updated 6 months ago
- Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs☆74Updated 5 months ago
- ☆36Updated last month
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆90Updated 4 months ago
- NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference☆61Updated last month
- ☆13Updated this week
- Fast Hadamard transform in CUDA, with a PyTorch interface☆111Updated 5 months ago
- Quantized Attention on GPU☆30Updated 2 weeks ago
- Applied AI experiments and examples for PyTorch☆166Updated 3 weeks ago