casper-hansen / AutoAWQ_kernels
☆69Updated 4 months ago
Alternatives and similar repositories for AutoAWQ_kernels:
Users that are interested in AutoAWQ_kernels are comparing it to the libraries listed below
- ☆74Updated 3 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆108Updated 2 weeks ago
- An easy-to-use package for implementing SmoothQuant for LLMs☆95Updated 10 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆106Updated 6 months ago
- ☆23Updated last month
- ☆181Updated 5 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆66Updated 9 months ago
- ☆62Updated last month
- 📚FFPA(Split-D): Yet another Faster Flash Prefill Attention with O(1) GPU SRAM complexity for headdim > 256, ~2x↑🎉vs SDPA EA.☆154Updated this week
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆240Updated 5 months ago
- ☆88Updated 6 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆77Updated 4 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆71Updated 6 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆110Updated 3 months ago
- A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.☆164Updated 3 weeks ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆101Updated 8 months ago
- ☆40Updated last week
- Official PyTorch implementation of FlatQuant: Flatness Matters for LLM Quantization☆112Updated this week
- ☆125Updated 3 weeks ago
- KV cache compression for high-throughput LLM inference☆117Updated last month
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆35Updated 2 weeks ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆123Updated last month
- DeeperGEMM: crazy optimized version☆61Updated last week
- ☆65Updated 2 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆44Updated 8 months ago
- A safetensors extension to efficiently store sparse quantized tensors on disk☆91Updated this week
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆104Updated this week
- Fast low-bit matmul kernels in Triton☆272Updated this week
- ☆51Updated 2 weeks ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆234Updated last month