xuyexiong 0777e2f899 Optimize torchair kv_consumer padding logic (#3526) ...

### What this PR does / why we need it?
Optimize torchair kv_consumer padding logic. Only pad when it is spec
decoding

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

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

Signed-off-by: xuyexiong <xuyexiong@huawei.com>

2025-10-18 16:42:17 +08:00

..

attention

[Core]Append padding logic for Attention (#3256)

2025-10-17 21:56:01 +08:00

compilation

[Feat]Make full graph mode compalible with MTP (#3276)

2025-10-17 20:19:56 +08:00

core

[Bugfix] Route requests requiring KVC recomputation from the decode instance to the P instance (#3448)

2025-10-18 15:56:44 +08:00

device_allocator

[Misc]Clean up useless import from vllm (#2049)

2025-07-28 16:01:59 +08:00

distributed

[BugFix]GPQA Accuracy Issue Bugfix (#3476)

2025-10-15 23:28:17 +08:00

eplb

[BugFix]Support redundant experts in EPLB (#3473)

2025-10-18 00:09:16 +08:00

lora

[Bugfix][LoRA] Fix forward error and shape mismatch when using LoRA (#3153)

2025-09-28 17:30:50 +08:00

models

[Feat]mtp aclgraph support (#3244)

2025-10-17 18:14:49 +08:00

multistream

[Quickfix] update CachedRequestState as NewRequestData changed (#2367)

2025-08-15 07:35:27 +08:00

ops

[BugFix]Support redundant experts in EPLB (#3473)

2025-10-18 00:09:16 +08:00

patch

[Refactor] Adapt deepseek-v3.2 to vllm 0.11.0 (#3432)

2025-10-15 17:48:58 +08:00

quantization

[BugFix]Support redundant experts in EPLB (#3473)

2025-10-18 00:09:16 +08:00

sample

Drop 0.10.2 (#3284)

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

spec_decode

[Feat]mtp aclgraph support (#3244)

2025-10-17 18:14:49 +08:00

torchair

Optimize torchair kv_consumer padding logic (#3526)

2025-10-18 16:42:17 +08:00

worker

[BUGFIX] Mtp torchair pd fix (#3506)

2025-10-17 21:57:05 +08:00

__init__.py

[Refactor] Adapt deepseek-v3.2 to vllm 0.11.0 (#3432)

2025-10-15 17:48:58 +08:00

ascend_config.py

[Bugfix] Route requests requiring KVC recomputation from the decode instance to the P instance (#3448)

2025-10-18 15:56:44 +08:00

ascend_forward_context.py

[Bugfix] fix logging and d2h bug for flash comm1 (#3505)

2025-10-17 21:13:41 +08:00

envs.py

[Feat] Flash comm allgher ep (#3334)

2025-10-15 19:36:32 +08:00

meta_registration.py

Fix the bugs about operator registration by PyTorch Dispatcher (#2786)

2025-09-13 11:58:52 +08:00

platform.py

[Bugfix] Route requests requiring KVC recomputation from the decode instance to the P instance (#3448)

2025-10-18 15:56:44 +08:00

utils.py

[Bugfix] fix logging and d2h bug for flash comm1 (#3505)

2025-10-17 21:13:41 +08:00