This is stars and forks stats for /mit-han-lab/llm-awq repository. As of 10 May, 2024 this repository has 893 stars and 66 forks.
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration [Paper] Efficient and accurate low-bit weight quantization (INT3/4) for LLMs, supporting instruction-tuned models and multi-modal LMs. The current release supports: AWQ search for accurate quantization. Pre-computed AWQ model zoo for LLMs (LLaMA-1&2, OPT, Vicuna, LLaVA; load to generate quantized weights). Memory-efficient 4-bit Linear in PyTorch. Efficient CUDA kernel implementation for fast inference (support context...
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration [Paper] Efficient and accurate low-bit weight quantization (INT3/4) for LLMs, supporting instruction-tuned models and multi-modal LMs. The current release supports: AWQ search for accurate quantization. Pre-computed AWQ model zoo for LLMs (LLaMA-1&2, OPT, Vicuna, LLaVA; load to generate quantized weights). Memory-efficient 4-bit Linear in PyTorch. Efficient CUDA kernel implementation for fast inference (support context...
repo | techs | stars | weekly | forks | weekly |
---|---|---|---|---|---|
facebookresearch/hiera | Python | 600 | 0 | 23 | 0 |
KasperskyLab/triangle_check | Python | 341 | 0 | 25 | 0 |
emarco177/ice_breaker | PythonHTMLCSS | 164 | 0 | 273 | 0 |
vincentarelbundock/modelsummary | RHTMLTeX | 794 | 0 | 69 | 0 |
bytebeamio/rumqtt | RustOther | 1.2k | 0 | 191 | 0 |
SFDigitalServices/sf-dahlia-web | SCSSCoffeeScriptTypeScript | 29 | 0 | 17 | 0 |
movie-web/movie-web | TypeScriptOther | 1.3k | 0 | 235 | 0 |
noahspurrier/dotfiles | Vim ScriptShellPython | 1 | 0 | 0 | 0 |
htphongx4/vue3-ts-vite-boilerplate | VueTypeScriptMDX | 66 | 0 | 34 | 0 |
parity-asia/hackathon-2023-summer | RustTypeScriptCSS | 14 | 0 | 75 | 0 |