mirror of https://github.com/mudler/LocalAI.git synced 2026-02-04 11:42:57 -05:00

Files

Ettore Di Giacinto d6409bd2eb Revert "chore(deps): bump torch from 2.7.0 to 2.7.1+xpu in /backend/python/vllm in the pip group across 1 directory" (#8367 )

Revert "chore(deps): bump torch from 2.7.0 to 2.7.1+xpu in /backend/python/vl…"

This reverts commit 4c0e70086d.

2026-02-03 08:34:54 +01:00

backend.py

fix: vllm missing logprobs (#5279 )

2025-04-30 12:55:07 +00:00

install.sh

chore: Update to Ubuntu24.04 (cont #7423 ) (#7769 )

2026-01-06 15:26:42 +01:00

Makefile

feat(mlx): add mlx backend (#6049 )

2025-08-22 08:42:29 +02:00

README.md

refactor: move backends into the backends directory (#1279 )

2023-11-13 22:40:16 +01:00

requirements-after.txt

fix(python): move vllm to after deps, drop diffusers main deps

2024-08-07 23:34:37 +02:00

requirements-cpu.txt

Revert "chore(deps): bump torch from 2.7.0 to 2.7.1+xpu in /backend/python/vllm in the pip group across 1 directory" (#8367 )

2026-02-03 08:34:54 +01:00

requirements-cublas12-after.txt

fix(vllm): Update flash-attn to specific wheel URL

2025-11-21 18:06:46 +01:00

requirements-cublas12.txt

Revert "chore(deps): bump torch from 2.7.0 to 2.7.1+xpu in /backend/python/vllm in the pip group across 1 directory" (#8367 )

2026-02-03 08:34:54 +01:00

requirements-hipblas.txt

chore: Update to Ubuntu24.04 (cont #7423 ) (#7769 )

2026-01-06 15:26:42 +01:00

requirements-install.txt

feat: migrate python backends from conda to uv (#2215 )

2024-05-10 15:08:08 +02:00

requirements-intel.txt

feat(qwen-tts): add Qwen-tts backend (#8163 )

2026-01-23 15:18:41 +01:00

requirements.txt

chore(deps): bump grpcio from 1.75.1 to 1.76.0 in /backend/python/vllm (#6827 )

2025-10-27 21:31:47 +01:00

run.sh

feat: Add backend gallery (#5607 )

2025-06-15 14:56:52 +02:00

test.py

fix: vllm missing logprobs (#5279 )

2025-04-30 12:55:07 +00:00

test.sh

feat: Add backend gallery (#5607 )

2025-06-15 14:56:52 +02:00

README.md

Creating a separate environment for the vllm project

make vllm