linfeng-yuan deceefd305 [releases/v0.18.0][bugfix][eplb] remove unnecessary weight_scale wrap behaviour (#7732) ...

### What this PR does / why we need it?
This PR simplifies the apply method in w8a8_dynamic.py by removing the
conditional logic that used fused_w1_scale and fused_w2_scale based on
the fused_scale_flag. This redundant wrap behavior leads to EPLB break
in int8 quantization scenarios.

Cherry-picked from #7188. Note that only bugfix lines in that PR are
picked.

Signed-off-by: linfeng-yuan <1102311262@qq.com>

2026-03-30 16:16:03 +08:00

..

_310p

[310P]: add torch chunk gated delta rule and 910b parity ut (#7594)

2026-03-25 16:46:43 +08:00

_cann_ops_custom

[Kernel] add custom op GmmSwigluQuantWeightNzTensorList (#3804)

2025-11-28 18:06:39 +08:00

attention

[v0.18.0][Bugfix]Fix Error "AttributeError: 'AscendCompressedTensorsConfig' obiect has no attribute 'enabling_fa_quant'" (#7748)

2026-03-28 17:03:56 +08:00

compilation

[Feat][SP] Suport SP for VL MoE models (#7044)

2026-03-24 17:16:00 +08:00

core

[v0.18.0][Misc] Recompute scheduler upgrade to vLLM 0.18.0 (#7720)

2026-03-27 18:24:53 +08:00

device

[A5][bugfix] Fix fused MoE A5 MXFP8 scale normalization, load-balance routing and gating_topk ops (#7573)

2026-03-25 17:20:28 +08:00

device_allocator

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #2) (#5977)

2026-01-19 08:59:46 +08:00

distributed

[Lint]Add lint hooks for clang-format, shellcheck, forbidden imports, and boolean context manager checks (#7511)

2026-03-24 20:03:01 +08:00

eplb

[EPLB] Reduce the memory used for batch_isend_irecv (#7344)

2026-03-20 12:25:58 +08:00

kv_offload

upgrade to 0.18.0 (#7502)

2026-03-21 16:05:38 +08:00

lora

[Bugfix][LoRA] Fix the bug when runs Qwen3-Reranker-0.6B with LoRA. (#7156)

2026-03-15 17:55:42 +08:00

model_loader

[ModelLoader][Feature] Add rfork support for fast model loading (#7392)

2026-03-25 16:40:30 +08:00

ops

[v0.18.0][Bugfix] Fix the bug of MTP1 crashing in multiple concurrent scenarios. (#7699)

2026-03-27 14:13:12 +08:00

patch

[Bugfix][Platform] Fix GLM47 tool-call finish backfill (#7710)

2026-03-28 09:15:04 +08:00

quantization

[releases/v0.18.0][bugfix][eplb] remove unnecessary weight_scale wrap behaviour (#7732)

2026-03-30 16:16:03 +08:00

sample

[Feature] Add docs of batch invariance and make some extra operators patch (#6910)

2026-03-05 09:12:40 +08:00

spec_decode

[v0.18.0][Bugfix][EAGLE] Fix FIA pad bug under max concurrency (#7754)

2026-03-29 12:23:44 +08:00

worker

[Bugfix]v0.18.0 support FlashComm1 & DCP for Qwen (#7726)

2026-03-29 15:59:19 +08:00

xlite

Main2main upgrade to vllm 0317 afternoon (#7409)

2026-03-18 23:24:27 +08:00

__init__.py

[ModelLoader][Feature] Add rfork support for fast model loading (#7392)

2026-03-25 16:40:30 +08:00

ascend_config.py

[feat] support dispatch_v2/combine_v2 hierarchy communication (#7698)

2026-03-27 09:20:16 +08:00

ascend_forward_context.py

[Bugfix][eager][oom] fix rank0 load imbalance by no padding when multi dp (#7297)

2026-03-23 17:05:02 +08:00

batch_invariant.py

[CI] Add pre-commit check for patch logger (#7446)

2026-03-19 16:53:20 +08:00

cpu_binding.py

[CPU binding] Implement global CPU slicing and improve IRQ binding for Ascend NPUs (#6945)

2026-03-03 17:20:52 +08:00

envs.py

[Misc] Drop Prefetch MLP Env (#7357)

2026-03-19 14:27:27 +08:00

flash_common3_context.py

[Lint]Style: Convert vllm-ascend/compilation to ruff format (#5912)

2026-01-16 20:57:46 +08:00

meta_registration.py

[Ops][Refactor] Remove custom rotary_embedding operator (#6523)

2026-02-07 09:24:05 +08:00

platform.py

[feat] support dispatch_v2/combine_v2 hierarchy communication (#7698)

2026-03-27 09:20:16 +08:00

profiling_config.py

[Core][Misc] Clean up ProfileExecuteDuration (#6461)

2026-02-01 20:06:01 +08:00

utils.py

[feat] support dispatch_v2/combine_v2 hierarchy communication (#7698)

2026-03-27 09:20:16 +08:00