yupeng 830f39dd70 [Bugfix][LoRA] Fix the issue when enable LoRA + tp + fully_sharded_loras (#6650) ...

### What this PR does / why we need it?
Fix the issue #6143 .

### Does this PR introduce _any_ user-facing change?
Allow to start the server with "--enable-lora && --fully-sharded-loras
&& --tensor_parallel_size 2".

### How was this patch tested?
pytest -sv tests/e2e/multicard/2-cards/test_llama32_lora_tp2.py
- vLLM version: v0.15.0
- vLLM main:
d7e17aaacd

---------

Signed-off-by: paulyu12 <507435917@qq.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>

2026-03-11 15:43:15 +08:00

..

dockerfiles

[Main2Main] Upgrade vLLM to 0303 (#6944)

2026-03-06 09:08:52 +08:00

matchers

[Lint]Style: reformat markdown files via markdownlint (#5884)

2026-01-15 09:06:01 +08:00

misc

[Misc] Download on both hk and guiyang region (#7129)

2026-03-10 19:22:32 +08:00

scripts

[Bugfix][LoRA] Fix the issue when enable LoRA + tp + fully_sharded_loras (#6650)

2026-03-11 15:43:15 +08:00

_e2e_nightly_multi_node.yaml

[CI]Upgrade niglty multi-node-tests max-parallel to 2 (#7035)

2026-03-10 16:25:51 +08:00

_e2e_nightly_single_node_models.yaml

[CI] support nightly ci for per pr by labels (#6483)

2026-03-05 16:46:37 +08:00

_e2e_nightly_single_node.yaml

[CI] support nightly ci for per pr by labels (#6483)

2026-03-05 16:46:37 +08:00

_e2e_test.yaml

[Test] Add e2e test cases for the Qwen-VL model adaptation to Ascend 310p (#6977)

2026-03-06 14:25:10 +08:00

_pre_commit.yml

[main2main] upgrade vllm main 0202 (#6560)

2026-02-05 19:31:17 +08:00

_schedule_image_build.yaml

[CI] Bump docker/metadata-action from 5 to 6 (#7069)

2026-03-10 09:06:04 +08:00

_unit_test.yaml

[CI] Skip test_mooncake_layerwise_connector.py in ut (#7147)

2026-03-11 11:46:29 +08:00

bot_merge_conflict.yaml

[CI] Improve CI (#5078)

2025-12-19 15:34:35 +08:00

bot_pr_create.yaml

[Main2Main] Upgrade vLLM to 0303 (#6944)

2026-03-06 09:08:52 +08:00

labled_doctest.yaml

[CI]Fixed the spell check function in typos.toml (#6753)

2026-02-14 11:57:26 +08:00

labled_download_model.yaml

[Misc] Download on both hk and guiyang region (#7129)

2026-03-10 19:22:32 +08:00

pr_close_cancel_job.yaml

Bump actions/github-script from 7 to 8 (#5796)

2026-01-12 20:44:02 +08:00

pr_test_full.yaml

[Main2Main] Upgrade vLLM to 0303 (#6944)

2026-03-06 09:08:52 +08:00

pr_test_light.yaml

[Test] Add e2e test cases for the Qwen-VL model adaptation to Ascend 310p (#6977)

2026-03-06 14:25:10 +08:00

READMD.md

[CI]Disable early exit to complete all tests (#6482)

2026-02-03 11:25:51 +08:00

schedule_codecov_refresh.yaml

[Main2Main] Upgrade vLLM to 0303 (#6944)

2026-03-06 09:08:52 +08:00

schedule_image_build_and_push.yaml

[CI] Build Image for v0.16.0rc1 (#7155)

2026-03-11 14:48:50 +08:00

schedule_lint_image_build.yaml

[CI] Bump docker/metadata-action from 5 to 6 (#7069)

2026-03-10 09:06:04 +08:00

schedule_nightly_image_build.yaml

[CI] Upgrade CANN to 8.5.1 (#6897)

2026-03-03 09:02:42 +08:00

schedule_nightly_test_a2.yaml

[CI]Upgrade niglty multi-node-tests max-parallel to 2 (#7035)

2026-03-10 16:25:51 +08:00

schedule_nightly_test_a3.yaml

[CI]Upgrade niglty multi-node-tests max-parallel to 2 (#7035)

2026-03-10 16:25:51 +08:00

schedule_release_code_and_wheel.yml

Bump actions/upload-artifact from 6 to 7 (#6906)

2026-03-02 14:08:28 +08:00

schedule_test_benchmarks.yaml

[CI] Upgrade CANN to 8.5.1 (#6897)

2026-03-03 09:02:42 +08:00

schedule_test_vllm_main.yaml

[CI] Upgrade CANN to 8.5.1 (#6897)

2026-03-03 09:02:42 +08:00

schedule_update_estimated_time.yaml

[CI] Bump actions/checkout from 4 to 6 (#7070)

2026-03-10 09:05:22 +08:00