meihanc 5b8e47cb68 [bugfix]Fix no attribute 'data' when MLAPO is enable (#6601) ...

### What this PR does / why we need it?

This PR fixes an `AttributeError: 'Parameter' object has no attribute
'data'` that occurs when MLAPO is enabled with vLLM v0.15.0.

The error is caused by a monkey-patch on
`MLAAttention.process_weights_after_loading` which is incompatible with
changes in vLLM v0.15.0. This is likely related to PyTorch's deprecation
of the `.data` attribute on `torch.nn.Parameter` objects.

This change makes the monkey-patch conditional, so it is not applied for
vLLM v0.15.0 and newer versions, resolving the crash.


- vLLM version: v0.15.0
- vLLM main:
d7e17aaacd

Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>

2026-02-10 09:04:32 +08:00

..

fused_moe

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #11) (#6176)

2026-02-06 15:28:49 +08:00

triton

perf: adaptive block size selection in linear_persistent kernel (#6537)

2026-02-04 21:36:26 +08:00

__init__.py

[Lint]Style: Convert vllm-ascend/ to ruff format(new Batch #8) (#6604)

2026-02-07 09:16:07 +08:00

activation.py

[Lint]Style: Convert vllm-ascend/ to ruff format(new Batch #8) (#6604)

2026-02-07 09:16:07 +08:00

flashcomm2_oshard_manager.py

[Lint]Style: Convert vllm-ascend/ to ruff format(new Batch #8) (#6604)

2026-02-07 09:16:07 +08:00

layer_shard_linear.py

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #10) (#6173)

2026-02-06 15:35:06 +08:00

layernorm.py

[Lint]Style: Convert vllm-ascend/ to ruff format(new Batch #8) (#6604)

2026-02-07 09:16:07 +08:00

linear_op.py

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #10) (#6173)

2026-02-06 15:35:06 +08:00

linear.py

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #10) (#6173)

2026-02-06 15:35:06 +08:00

mla.py

[bugfix]Fix no attribute 'data' when MLAPO is enable (#6601)

2026-02-10 09:04:32 +08:00

mm_encoder_attention.py

[MISC] Clean up useless env USE_OPTIMIZED_MODEL (#6618)

2026-02-09 15:38:58 +08:00

register_custom_ops.py

[Lint]Style: Convert vllm-ascend/ to ruff format(new Batch #8) (#6604)

2026-02-07 09:16:07 +08:00

rotary_embedding.py

[BugFix] Add support for rotary_dim parameter when using partial rope in rotary_embedding (#6581)

2026-02-09 17:17:52 +08:00

vocab_parallel_embedding.py

[Lint]Style: Convert vllm-ascend/ to ruff format(new Batch #8) (#6604)

2026-02-07 09:16:07 +08:00

weight_prefetch.py

[Lint]Style: Convert vllm-ascend/ to ruff format(new Batch #8) (#6604)

2026-02-07 09:16:07 +08:00