xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-13 18:35:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

[V1] TPU - Enable prefix caching by default (#14773)

Browse Source
This commit is contained in:
Alexander Matveev 2025-03-13 23:40:05 -04:00 committed by GitHub
parent 60c872d4b6
commit 7888e1d0a3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/platforms/tpu.py
View File

@ -108,12 +108,6 @@ class TpuPlatform(Platform):
parallel_config.worker_cls = \ parallel_config.worker_cls = \
"vllm.worker.tpu_worker.TPUWorker" "vllm.worker.tpu_worker.TPUWorker"
# Adjust scheduler config for V1
# TODO: Add support for these
if envs.VLLM_USE_V1 and vllm_config.cache_config.enable_prefix_caching:
logger.warning("[V1][TPU] Disable prefix caching")
vllm_config.cache_config.enable_prefix_caching = False
assert not vllm_config.speculative_config, ( assert not vllm_config.speculative_config, (
"Speculative decoding is not yet supported for TPU backend") "Speculative decoding is not yet supported for TPU backend")