mit-han-lab / tinychat-tutorial

Related projects: ⓘ

• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆82Updated 6 months ago
• mit-han-lab / parallel-computing-tutorial
  ☆134Updated last year
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆93Updated last week
• ankan-ban / llama_cu_awq
  llama INT4 cuda inference with AWQ
  ☆46Updated 2 months ago
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆35Updated 4 months ago
• Qualcomm-AI-research / FP8-quantization
  ☆113Updated last year
• DD-DuDa / BitDistiller
  [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.
  ☆69Updated 4 months ago
• AlibabaPAI / FLASHNN
  ☆67Updated last week
• wimh966 / outlier_suppression
  The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer L…
  ☆46Updated last year
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆81Updated 2 months ago
• weishengying / cutlass_flash_atten_fp8
  使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention
  ☆46Updated last month
• Bruce-Lee-LY / flash_attention_inference
  Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.
  ☆20Updated last week
• IntelLabs / FP8-Emulation-Toolkit
  PyTorch extension for emulating FP8 data formats on standard FP32 Xeon/GPU hardware.
  ☆98Updated 9 months ago
• Bruce-Lee-LY / cuda_hgemv
  Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.
  ☆40Updated last week
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆173Updated 3 months ago
• TiledTensor / TiledCUDA
  TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.
  ☆114Updated last week
• LeiWang1999 / tvm_gpu_gemm
  play gemm with tvm
  ☆81Updated last year
• triton-lang / kernels
  ☆27Updated 3 weeks ago
• uwsampl / SparseTIR
  SparseTIR: Sparse Tensor Compiler for Deep Learning
  ☆129Updated last year
• mit-han-lab / lmquant
  ☆102Updated 3 months ago
• chenhongyu2048 / LLM-inference-optimization-paper
  Summary of some awesome work for optimizing LLM inference
  ☆26Updated this week
• ModelTC / awesome-lm-system
  Summary of system papers/frameworks/codes/tools on training or serving large model
  ☆56Updated 9 months ago
• LeiWang1999 / Stream-k.tvm
  ☆14Updated last week
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆50Updated 3 months ago
• bytedance / ABQ-LLM
  ☆23Updated this week
• Dao-AILab / fast-hadamard-transform
  Fast Hadamard transform in CUDA, with a PyTorch interface
  ☆87Updated 3 months ago
• mit-han-lab / Quest
  [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
  ☆161Updated 2 months ago
• Raincleared-Song / sparse_gpu_operator
  GPU operators for sparse tensor operations
  ☆27Updated 6 months ago
• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆166Updated 11 months ago
• ColfaxResearch / cutlass-kernels
  ☆138Updated 2 months ago