Small cleanup. (#1560)

Using a single `os.getenv` statement instead of multiple.
Should make truthful values easier to catch

In the end didn't move towards full CLI because modifying globals in
Python is error prone (depends on code import order).

Added an error when mamba is launched with TP.


# 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

 -->
This commit is contained in:
Nicolas Patry 2024-02-14 15:30:07 +01:00 committed by GitHub
parent d6b0fb9e25
commit 4c2848b24b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 10 additions and 5 deletions

View File

@ -28,7 +28,7 @@ from text_generation_server.models.cache_manager import (
BLOCK_SIZE,
)
from text_generation_server.pb import generate_pb2
from text_generation_server.models.globals import MEM_POOL
from text_generation_server.models.globals import MEM_POOL, ENABLE_CUDA_GRAPHS
from text_generation_server.utils import StoppingCriteria, HeterogeneousNextTokenChooser
from text_generation_server.utils.dist import MEMORY_FRACTION
@ -793,7 +793,7 @@ class FlashCausalLM(Model):
self.device,
)
if os.getenv("ENABLE_CUDA_GRAPHS", "False") == "True":
if ENABLE_CUDA_GRAPHS:
try:
logger.info("Experimental support for Cuda Graphs is enabled")
# Warmup cuda graphs

View File

@ -1,3 +1,6 @@
import torch
import os
MEM_POOL = torch.cuda.graph_pool_handle()
# This is overridden by the cli
ENABLE_CUDA_GRAPHS = os.getenv("ENABLE_CUDA_GRAPHS", "false").lower() in {"1", "true"}

View File

@ -13,7 +13,7 @@ from text_generation_server.utils import (
weight_files,
Weights,
)
from text_generation_server.models.globals import MEM_POOL
from text_generation_server.models.globals import ENABLE_CUDA_GRAPHS, MEM_POOL
import time
from text_generation_server.models.custom_modeling.mamba_modeling import MambaModel, InferenceParams
from text_generation_server.models import Model
@ -377,7 +377,9 @@ class Mamba(Model):
dtype: Optional[torch.dtype] = None,
trust_remote_code: bool = False,
):
self.process_group, _rank, _world_size = initialize_torch_distributed()
self.process_group, _rank, world_size = initialize_torch_distributed()
if world_size > 1:
raise RuntimeError("Mamba does not support Tensor Parallelism (TP)")
self.cuda_graphs = {}
if torch.cuda.is_available():
device = torch.device("cuda")
@ -427,7 +429,7 @@ class Mamba(Model):
def warmup(self, batch) -> Optional[int]:
# TODO: implement warmup for Mamba if needed
if os.getenv("ENABLE_CUDA_GRAPHS", "False") == "True":
if ENABLE_CUDA_GRAPHS:
if self.speculate is None or self.speculate == 0:
try:
logger.info("Experimental support for Cuda Graphs is enabled")