mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-24 00:12:08 +00:00
ba291dad9f
* Improve the handling of quantized weights Handling of quantized weights was split between two mechanisms: - For quantized checkpoints, we used the new weight loader infrastructure. - For quantization while loading (EETQ, FP8, bitsandbytes) we instead relied on conditional in `get_linear`. Weight loaders support context managers to selectively load particular layers with different weight loaders, which is useful for models like Idefics2 AWQ, which uses a quantized text model, but unquantized vision and connector models. However, the context manager would be overrided by `get_linear`, which string-checks `quantizer`. Also, the context manager would not work with EETQ, FP8, and bitsandbytes. This change migrates all quantizers to the weight loader infrastructure. This has several benefits: - We can use context managers with all quantizers. - All the implementation details move down to the quantizer layers, `get_linear` does not need to know how to handle quantizer linear layers. - All quantizer weights are strongly typed, we don't pass around raw tensors. - We don't have to pass around the `quantizer` string everywhere. * Exclude non-MLP layers when using FP8 quantization with Llama |
||
|---|---|---|
| .. | ||
| attention | ||
| awq | ||
| gptq | ||
| __init__.py | ||
| bnb.py | ||
| conv.py | ||
| eetq.py | ||
| exl2.py | ||
| fp8.py | ||
| layernorm.py | ||
| linear.py | ||
| lora.py | ||
| marlin.py | ||
| medusa.py | ||
| mlp.py | ||
| rotary.py | ||
| speculative.py | ||
| tensor_parallel.py | ||