mit-han-lab / tinychat-tutorialLinks
☆72Updated 9 months ago
Alternatives and similar repositories for tinychat-tutorial
Users that are interested in tinychat-tutorial are comparing it to the libraries listed below
Sorting:
- ☆81Updated 7 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆40Updated 2 months ago
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆71Updated last month
- ☆99Updated 2 weeks ago
- ☆172Updated 2 years ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆113Updated last year
- ☆92Updated 3 months ago
- llama INT4 cuda inference with AWQ☆54Updated 7 months ago
- 🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.☆211Updated 3 weeks ago
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆156Updated last month
- ☆63Updated 4 months ago
- GPTQ inference TVM kernel☆40Updated last year
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆55Updated 5 months ago
- GPU operators for sparse tensor operations☆34Updated last year
- Quantized Attention on GPU☆44Updated 9 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆107Updated 3 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆95Updated 2 months ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆148Updated 3 months ago
- ☆92Updated 5 months ago
- Implement Flash Attention using Cute.☆95Updated 8 months ago
- ☆158Updated 2 years ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆261Updated last month
- Fast Hadamard transform in CUDA, with a PyTorch interface☆224Updated last year
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆120Updated last year
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆57Updated 3 weeks ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆110Updated 11 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆81Updated last week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆319Updated last year
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆138Updated last week
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆110Updated 10 months ago