hf_text-generation-inference/integration-tests/pytest.ini

[pytest]
addopts = --snapshot-warn-unused
asyncio_mode = auto
markers =
    private: marks tests as requiring an admin hf token (deselect with '-m "not private"')
fix(server): fix init for flash causal lm (#352) Fixes #347 2023-05-22 07:05:32 -06:00			`[pytest]`
feat(server): Rework model loading (#344) # What does this PR do? Reworked the loading logic. Idea is to use cleaner loading code: - Remove need for `no_init_weights` - Remove all weird `bnb_linear` and `load_weights` and `post_load_weights`. New code layout: - New class `Weights` in charge of handling loading the weights from multiple files into appropiate tensors (potentially sharded) - TP layers now are "shells", they contain the code to know what kind of sharding we need + eventual `all_reduce`. They do not inherit from linear, but they contain some kind of Linear instead - the contained linear can be either FastLinear, BnbLinear or GPTq Linear next. - All modeling code is explictly made for sharding, process group is just no-ops for non sharded code (removes a lot of test cases) ![Screenshot from 2023-05-19 23-19-59](https://github.com/huggingface/text-generation-inference/assets/204321/9a802654-74a3-488c-87a8-073743a6143f) --------- Co-authored-by: Ubuntu <ubuntu@ip-172-31-41-161.taildb5d.ts.net> Co-authored-by: Ubuntu <ubuntu@ip-172-31-41-161.ec2.internal> Co-authored-by: OlivierDehaene <olivier@huggingface.co> Co-authored-by: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com> 2023-06-08 06:51:52 -06:00			`addopts = --snapshot-warn-unused`
fix(server): fix init for flash causal lm (#352) Fixes #347 2023-05-22 07:05:32 -06:00			`asyncio_mode = auto`
			`markers =`
chore: add pre-commit (#1569) 2024-02-16 03:58:58 -07:00			`private: marks tests as requiring an admin hf token (deselect with '-m "not private"')`