Pr0Wh1teGivee d13fb0766e [Perf] add patch to optimize apply_topk_topp (#1732) ...

### What this PR does / why we need it?
Performance optimization for apply_top_k_top_p
### Does this PR introduce _any_ user-facing change?
Use VLLM_ASCEND_ENABLE_TOPK_TOPP_OPTIMIZATION to enable this feature
### How was this patch tested?
e2e & ut

















- vLLM version: v0.9.2
- vLLM main:
6a9e6b2abf

Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>

2025-07-11 15:32:02 +08:00

..

attention

[Perf] Improve MLA multistream performance (#1353)

2025-07-11 08:51:17 +08:00

compilation

[CI] Upgrade vllm to 0.9.1 (#1165)

2025-06-11 16:33:11 +08:00

core

[AscendScheduler][Bugfix] Remove num_draft_tokens while allocating slots (#1718)

2025-07-10 18:47:45 +08:00

device_allocator

[Build] Add build info (#1386)

2025-06-27 09:14:43 +08:00

distributed

[1/N][CI] Move linting system to pre-commits hooks (#1256)

2025-07-10 14:17:15 +08:00

lora

[Bugfix] fix import error (#600)

2025-04-22 08:57:25 +08:00

models

rm router logits Improve TTOP 3ms (#1407)

2025-07-11 08:53:17 +08:00

multistream

[perf]: support dual-batch overlap(dbo) for deepseek (#941)

2025-06-07 16:46:58 +08:00

ops

use npu_moe_gating_top_k_softmax (#1355)

2025-07-11 08:55:06 +08:00

patch

[Perf] add patch to optimize apply_topk_topp (#1732)

2025-07-11 15:32:02 +08:00

pool

[Bugfix] Add func swap_states to fix MLA attention (#1580)

2025-07-02 17:42:53 +08:00

quantization

perf: use multicast to avoid padding decode request to prefill size (#1555)

2025-07-07 22:36:03 +08:00

sample

Spec decode support for V1 Engine (#874)

2025-05-23 14:25:46 +08:00

worker

Support pipeline parallel in V1 Engine (#1700)

2025-07-11 15:30:51 +08:00

__init__.py

[CI] Patch torch.library.infer_schema for fused moe ops to fix CI (#854)

2025-05-14 19:49:09 +08:00

ascend_config.py

[CI] Follow vLLM FusedMoEParallelConfig interface change and clean up unused config (#1625)

2025-07-04 17:54:33 +08:00

envs.py

[Perf] add patch to optimize apply_topk_topp (#1732)

2025-07-11 15:32:02 +08:00

platform.py

[CORE]initial support for torchair with non-mla backend (#1506)

2025-07-03 22:21:42 +08:00

utils.py

rm router logits Improve TTOP 3ms (#1407)

2025-07-11 08:53:17 +08:00