mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-24 00:12:08 +00:00
8511669cb2
Quantized weights were loaded in the `Weights` class, but this was getting quite unwieldy, where every higher level method to load weights was a long conditional to cover all the different quantizers. This change moves loading of quantized weights out of the `Weights` class. This is done by defining a simple `WeightsLoader` interface that is implemented by `Exl2WeightsLoader`, `GPTQWeightsLoader`, and `MarlinWeightsLoader`. These implementations are in the quantizers' respective modules. The `Weights` class provides the low-level load operations (such as loading tensors or sharded tensors), but delegates loads that need quantizer-specific weight processing to a loader. The loaders still use the low-level functionality provided by `Weights`. I initially tried making a hierarchy where a class like `GPTQWeights` would inherit from `Weights`. But it is not very flexible (e.g. does not work well with the new weight storage mock used in tests) and the implicit indirections made the code harder to follow. |
||
|---|---|---|
| .. | ||
| 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 | ||