hucong 292cf339c3 [BugFix][P/D] Modify the recalculation logic to prevent waiting requests from filling up the D node KVCache (#3641) ...

### What this PR does / why we need it?
Modify the recalculation logic to prevent waiting requests from filling
up the D node KVCache

- vLLM version: v0.11.0rc3
- vLLM main:
17c540a993

Signed-off-by: underfituu <hzhucong@163.com>

2025-10-25 09:14:20 +08:00

..

attention

[Refactor] Refactor Ascend attention implementation forward (#3714)

2025-10-25 08:58:35 +08:00

compilation

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

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

core

[BugFix][P/D] Modify the recalculation logic to prevent waiting requests from filling up the D node KVCache (#3641)

2025-10-25 09:14:20 +08:00

device_allocator

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

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

distributed

look up multi_tp key (#3699)

2025-10-24 17:23:36 +08:00

eplb

[CI]Add EPLB CI. (#3568)

2025-10-21 22:58:02 +08:00

kv_offload

[Feat] add native kvcache offload (#3433)

2025-10-22 14:15:49 +08:00

lora

[1/N][Refactor] Refactor code to adapt with vllm main (#3612)

2025-10-24 16:55:08 +08:00

model_loader

[Misc] Add a model loader that utilizes HCCL for weight loading (#2888)

2025-10-23 15:56:07 +08:00

models

[1/N][Refactor] Refactor code to adapt with vllm main (#3612)

2025-10-24 16:55:08 +08:00

multistream

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

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

ops

[Feat] Add mrope fusion op (#3708)

2025-10-25 09:12:18 +08:00

patch

[1/N][Refactor] Refactor code to adapt with vllm main (#3612)

2025-10-24 16:55:08 +08:00

quantization

[1/N][Refactor] Refactor code to adapt with vllm main (#3612)

2025-10-24 16:55:08 +08:00

sample

Drop 0.10.2 (#3284)

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

spec_decode

[1/N][Refactor] Refactor code to adapt with vllm main (#3612)

2025-10-24 16:55:08 +08:00

torchair

[Refactor] Refactor Ascend attention implementation forward (#3714)

2025-10-25 08:58:35 +08:00

worker

[Refactor] Refactor Ascend attention implementation forward (#3714)

2025-10-25 08:58:35 +08:00

__init__.py

[1/N][Refactor] Refactor code to adapt with vllm main (#3612)

2025-10-24 16:55:08 +08:00

ascend_config.py

[1/N][Refactor] Refactor code to adapt with vllm main (#3612)

2025-10-24 16:55:08 +08:00

ascend_forward_context.py

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

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

cpu_binding.py

[main] support cpu binding (#3546)

2025-10-21 09:17:03 +08:00

envs.py

support cp&dcp (#3260)

2025-10-24 10:32:01 +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

[Refactor] Refactor Ascend attention implementation forward (#3714)

2025-10-25 08:58:35 +08:00

utils.py

[Feat] Add mrope fusion op (#3708)

2025-10-25 09:12:18 +08:00