xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-28 05:47:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

[TPU] update torch_xla pin (#19231)

Browse Source 
Signed-off-by: Chengji Yao <chengjiyao@google.com>
This commit is contained in:
Chengji Yao 2025-06-05 21:27:38 -07:00 committed by GitHub
parent f8a1a2d108
commit b61dc5f972
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 8 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
requirements/tpu.txt
View File

@ -18,9 +18,9 @@ setuptools==78.1.0
--find-links https://storage.googleapis.com/libtpu-releases/index.html
--find-links https://storage.googleapis.com/jax-releases/jax_nightly_releases.html
--find-links https://storage.googleapis.com/jax-releases/jaxlib_nightly_releases.html
torch==2.8.0.dev20250529
torchvision==0.22.0.dev20250529
torch_xla[tpu, pallas] @ https://storage.googleapis.com/pytorch-xla-releases/wheels/tpuvm/torch_xla-2.8.0.dev20250529-cp39-cp39-linux_x86_64.whl ; python_version == "3.9"
torch_xla[tpu, pallas] @ https://storage.googleapis.com/pytorch-xla-releases/wheels/tpuvm/torch_xla-2.8.0.dev20250529-cp310-cp310-linux_x86_64.whl ; python_version == "3.10"
torch_xla[tpu, pallas] @ https://storage.googleapis.com/pytorch-xla-releases/wheels/tpuvm/torch_xla-2.8.0.dev20250529-cp311-cp311-linux_x86_64.whl ; python_version == "3.11"
torch==2.8.0.dev20250605
torchvision==0.23.0.dev20250605
torch_xla[tpu, pallas] @ https://storage.googleapis.com/pytorch-xla-releases/wheels/tpuvm/torch_xla-2.8.0.dev20250605-cp39-cp39-linux_x86_64.whl ; python_version == "3.9"
torch_xla[tpu, pallas] @ https://storage.googleapis.com/pytorch-xla-releases/wheels/tpuvm/torch_xla-2.8.0.dev20250605-cp310-cp310-linux_x86_64.whl ; python_version == "3.10"
torch_xla[tpu, pallas] @ https://storage.googleapis.com/pytorch-xla-releases/wheels/tpuvm/torch_xla-2.8.0.dev20250605-cp311-cp311-linux_x86_64.whl ; python_version == "3.11"

2
tests/tpu/test_moe_pallas.py
View File

@ -27,7 +27,7 @@ TOP_KS = [2, 6]
# The Pallas GMM kernel requires num_tokens * topk to be a multiple of 16
@pytest.mark.parametrize("m", [8, 16, 64, 2048])
@pytest.mark.parametrize("n", [128, 1024, 2048])
@pytest.mark.parametrize("k", [128, 512, 1024])
@pytest.mark.parametrize("k", [128, 511, 1024])
@pytest.mark.parametrize("e", NUM_EXPERTS)
@pytest.mark.parametrize("topk", TOP_KS)
@pytest.mark.parametrize("ep_size", EP_SIZE)

3
vllm/v1/worker/tpu_worker.py
View File

@ -100,7 +100,8 @@ class TPUWorker:
# `xla_tpu_force_1d_allreduce_at_chunk_count` is a temporary solution to
# fix this. It will be removed after the bug in XLA compiler is fixed.
os.environ["LIBTPU_INIT_ARGS"] = (
"--xla_tpu_force_1d_allreduce_at_chunk_count=1")
os.environ.get("LIBTPU_INIT_ARGS", "") +
" --xla_tpu_force_1d_allreduce_at_chunk_count=1")
torch.set_grad_enabled(False)
torch.set_default_dtype(self.model_config.dtype)