ankan-ban / llama_cu_awq
llama INT4 cuda inference with AWQ
☆53Updated 2 months ago
Alternatives and similar repositories for llama_cu_awq:
Users that are interested in llama_cu_awq are comparing it to the libraries listed below
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆91Updated last week
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆62Updated 7 months ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆103Updated 8 months ago
- ☆50Updated 2 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆108Updated 6 months ago
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆59Updated 6 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆65Updated last week
- ☆91Updated 6 months ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆35Updated last month
- PyTorch bindings for CUTLASS grouped GEMM.☆77Updated 5 months ago
- Benchmark code for the "Online normalizer calculation for softmax" paper☆87Updated 6 years ago
- ☆68Updated 2 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆35Updated 3 weeks ago
- ☆94Updated 3 weeks ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆32Updated last week
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆77Updated this week
- play gemm with tvm☆89Updated last year
- ☆60Updated 3 months ago
- Implement Flash Attention using Cute.☆74Updated 3 months ago
- GPTQ inference TVM kernel☆38Updated 11 months ago
- ☆29Updated 11 months ago
- DeeperGEMM: crazy optimized version☆64Updated this week
- ☆76Updated last week
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆25Updated last week
- An extention of TVMScript to write simple and high performance GPU kernels with tensorcore.☆51Updated 8 months ago
- ☆193Updated 8 months ago
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆17Updated 6 months ago
- ☆76Updated 4 months ago
- ☆53Updated last year
- ☆19Updated 6 months ago