- The code is relatively easy (just disable the checks on Embedding and
Head)
This cannot be done in the same easy fashion for hidden_dim/head_dim.
It's relatively easy on some models (classic MHA) but it would make the
other
models (MQA) much more complex, and GPTQ quantization another quite
hairy piece
of code.
# What does this PR do?
This fixes a typo and extends the GPTP_BITS environment variables
through to the second method which requires the same logic. Please let
me know if there's anything I've misunderstood in this change.
Thanks @Narsil for the original fix.
# What does this PR do?
Some models are already converted, and do not have those values in the
file, this enables users to use them with less friction.
Went for pure env based because adding flags would end up (imo) very
tedious to maintain. There's a lot of sanitation to do: those flags
would be errors if not used in conjuction with `--quantize gptq`.
Then the flags need to exist in the launcher and the server passing them
all throughout all function calls.
This PR is intended as an easy escape hatch, not the defacto method to
use gptq in TGI.
Fixes#500
# What does this PR do?
In title. Adds argument `--hostname` in router to support something like
`--hostname ::`. Tested with
```commandline
cargo run -- --port 8080 --hostname ::
curl -I -X GET 'http://[::1]:8080/health' # failed before this commit
```
Trigger CI
---------
Co-authored-by: Phil Chen <philchen2000@gmail.com>
This PR allows the MPT model to be loaded from local files. Without this
change, an exception will be thrown by `hf_hub_download` function if
`model_id` is a local path.
# What does this PR do?
For consistency and ease of use (you can just run `make` to install vllm
without any extra steps).
<!--
Congratulations! You've made it this far! You're not quite done yet
though.
Once merged, your PR is going to appear in the release notes with the
title you set, so make sure it's a great title that fully reflects the
extent of your awesome contribution.
Then, please replace this with a description of the change and which
issue is fixed (if applicable). Please also include relevant motivation
and context. List any dependencies (if any) that are required for this
change.
Once you're done, someone will review your PR shortly (see the section
"Who can review?" below to tag some potential reviewers). They may
suggest changes to make the code even better. If no one reviewed your PR
after a week has passed, don't hesitate to post a new comment
@-mentioning the same persons---sometimes notifications get lost.
-->
<!-- Remove if not applicable -->
Fixes # (issue)
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Did you read the [contributor
guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
Pull Request section?
- [ ] Was this discussed/approved via a Github issue or the
[forum](https://discuss.huggingface.co/)? Please add a link
to it if that's the case.
- [ ] Did you make sure to update the documentation with your changes?
Here are the
[documentation
guidelines](https://github.com/huggingface/transformers/tree/main/docs),
and
[here are tips on formatting
docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
- [ ] Did you write any new necessary tests?
## Who can review?
Anyone in the community is free to review the PR once the tests have
passed. Feel free to tag
members/contributors who may be interested in your PR.
<!-- Your PR will be replied to more quickly if you can figure out the
right person to tag with @
@OlivierDehaene OR @Narsil
-->
# This PR adds an http header option to disable buffering for the
generate_stream endpoint response stream.
Problem: If a model is run behind a proxy server such as nginx that has
buffering enabled then the response stream from generate_stream gets
aggregated into a single response which basically disables streaming.
Instead of getting a chunked response where each token is presented over
time the response presents everything all at once.
Solution: This change adds the `X-Accel-Buffering` http header which
disables buffering for the generate_stream response, allowing the
response to stream properly.
Let's start discussing implementation.
- Need to expose the quantization scripts (either included here or add
doc on how to use https://github.com/qwopqwop200/GPTQ-for-LLaMa)
- Make sure GPTQ works for multiple models (priority to Falcon).
Currently it means that every place we use `get_{tensor|sharded}` to
check for quantization.
My idea is to reintegrate as much as possible into `utils/layer.py` by
expanding `load_multi` to be a bit more generic.
This might require some thinking, but ultimately the
`qweight,qzeros,scales,g_idx` should be in a single place, and
independant of bias presence.
# What does this PR do?
<!--
Congratulations! You've made it this far! You're not quite done yet
though.
Once merged, your PR is going to appear in the release notes with the
title you set, so make sure it's a great title that fully reflects the
extent of your awesome contribution.
Then, please replace this with a description of the change and which
issue is fixed (if applicable). Please also include relevant motivation
and context. List any dependencies (if any) that are required for this
change.
Once you're done, someone will review your PR shortly (see the section
"Who can review?" below to tag some potential reviewers). They may
suggest changes to make the code even better. If no one reviewed your PR
after a week has passed, don't hesitate to post a new comment
@-mentioning the same persons---sometimes notifications get lost.
-->
<!-- Remove if not applicable -->
Fixes # (issue)
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Did you read the [contributor
guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
Pull Request section?
- [ ] Was this discussed/approved via a Github issue or the
[forum](https://discuss.huggingface.co/)? Please add a link
to it if that's the case.
- [ ] Did you make sure to update the documentation with your changes?
Here are the
[documentation
guidelines](https://github.com/huggingface/transformers/tree/main/docs),
and
[here are tips on formatting
docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
- [ ] Did you write any new necessary tests?
## Who can review?
Anyone in the community is free to review the PR once the tests have
passed. Feel free to tag
members/contributors who may be interested in your PR.
<!-- Your PR will be replied to more quickly if you can figure out the
right person to tag with @
@OlivierDehaene OR @Narsil
-->
---------
Co-authored-by: Ubuntu <ubuntu@ip-172-31-41-161.ec2.internal>
Co-authored-by: OlivierDehaene <olivier@huggingface.co>
Should be more robust to shared tensors (ok when using
`from_pretrained). But forcing us to add new checks in our loading
code (since the chosen key to keep might be different from
`transformers`).
---------
Co-authored-by: Ubuntu <ubuntu@ip-172-31-41-161.ec2.internal>
# What does this PR do?
This PR fixes:
- The usage of non posix comparison which may fail depending on the
shell used (`=` will always work, `==` only with bash)
- Typo in the env variable name displayed in the error message
`BUILD_EXTENSION` instead of `BUILD_EXTENSIONS`
<!-- Remove if not applicable -->
Fixes#422
# What does this PR do?
It solves a typo in the comment sections referencing the environment
variable `CUDA_VISIBLE_DEVICES`. No misspelling references to this
variable have been found in code logic leading to undefined behaviour or
bugs. This PR is not expected to perform any code logic modification.
# 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)
---------
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>
Nicolas Patry