mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-31 02:18:50 -04:00
24c16c9bb5
Bumps [vllm](https://github.com/vllm-project/vllm) from 0.25.0 to 0.25.1. - [Release notes](https://github.com/vllm-project/vllm/releases) - [Changelog](https://github.com/vllm-project/vllm/blob/main/RELEASE.md) - [Commits](https://github.com/vllm-project/vllm/compare/v0.25.0...v0.25.1) --- updated-dependencies: - dependency-name: vllm dependency-version: 0.25.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
13 lines
750 B
Plaintext
13 lines
750 B
Plaintext
# vLLM 0.20+ ships an aarch64 manylinux wheel on PyPI whose Requires-Dist pins
|
|
# torch==2.11.0 / torchvision==0.26.0 / torchaudio==2.11.0, locking an ABI-
|
|
# consistent set with the cu130 torch wheel installed above.
|
|
#
|
|
# Pinned to match the cublas13 build (requirements-cublas13-after.txt) and to
|
|
# stay deterministic on GB10 / DGX Spark: 0.24.0 carries vllm-project/vllm#45179
|
|
# ("release cached device memory under pressure on UMA GPUs during weight
|
|
# loading"), without which cold model loads on the Grace Blackwell unified-
|
|
# memory architecture crash deterministically with an empty "Engine core init
|
|
# failed" set (mudler/LocalAI#10722). Leaving this unpinned let the L4T image
|
|
# drift onto whatever wheel was latest at build time.
|
|
vllm==0.25.1
|