LocalAI

mirror of https://github.com/mudler/LocalAI.git synced 2026-08-04 12:22:22 -04:00

Author	SHA1	Message	Date
localai-org-maint-bot	9ac8bfcdd0	fix(vllm): restore CPU torch build The CPU requirements were updated to an XPU-only torch wheel, which cannot resolve from the configured CPU index and also breaks vLLM's pinned CPU wheel compatibility. Restore the supported CPU pin; Intel continues to obtain its XPU torch dependency from upstream requirements/xpu.txt. Assisted-by: Codex:gpt-5	2026-07-30 05:08:01 +00:00
localai-org-maint-bot	bdefd28d84	Merge master into dependabot/pip/backend/python/vllm/torch-2.13.0xpu Assisted-by: Codex:gpt-5	2026-07-30 05:08:01 +00:00
localai-org-maint-bot	5910d4e0a1	Merge branch 'master' into dependabot/pip/backend/python/vllm/torch-2.13.0xpu	2026-07-29 15:04:51 +02:00
dependabot[bot]	09aab62fdb	chore(deps): bump torch in /backend/python/vllm Bumps torch from 2.9.1+cpu to 2.13.0+xpu. --- updated-dependencies: - dependency-name: torch dependency-version: 2.13.0+xpu dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com>	2026-07-29 09:06:50 +00:00

Compare commits