Yizhou 4536123341 [Fix] Fix mc2_tokens_capacity-related issues (#3411) ...

### What this PR does / why we need it?
Replaces the hardcoded `mc2_tokens_capacity` with the max graph capture
size for a more accurate allocation.

This change ensures the capacity is correctly sized relative to the
graph capture configuration, removing a magic number and making the
setup more robust.

This PR fixes two issues:

1. <del>MC2 op restrictions differ between SoCs.</del> @Angazenn This
requires an overhaul, hence removed from this PR, please commit another
PR.
2. The hardcoded value `512` allocates too much buffer for large models.

### Does this PR introduce _any_ user-facing change?
None.

### How was this patch tested?
Tested in daily checks.


- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

---------

Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>

2025-10-14 10:56:12 +08:00

..

__init__.py

[Misc][V0 Deprecation] Remove Cache Engine Used for V0 Worker (#1878)

2025-07-19 09:42:32 +08:00

block_table.py

[HybridKV] Fix prefill disaggregation kvcache addr alignment & use hybrid kv cache only when running qwen3_next (#3007)

2025-09-18 21:43:22 +08:00

model_runner_v1.py

[Fix] Fix mc2_tokens_capacity-related issues (#3411)

2025-10-14 10:56:12 +08:00

npu_input_batch.py

Drop 0.10.2 (#3284)

2025-10-09 10:28:38 +08:00

worker_v1.py

[Aclgraph][DP] Fix dp dummy run not in aclgraph error (#3208)

2025-09-30 11:14:51 +08:00