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

 -->

Author: Narsil

server/text_generation_server/models/flash_causal_lm.py

@@ -28,7 +28,7 @@
     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 @@ def warmup(self, batch: FlashCausalLMBatch):
             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

server/text_generation_server/models/globals.py

@@ -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"}

server/text_generation_server/models/mamba.py

@@ -13,7 +13,7 @@
     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 @@ def __init__(
         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 @@ def batch_type(self) -> Type[MambaBatch]:
 
     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")