wangbj127 9fd01a52c0 [v0.18.0][BugFix] Fix DSV3.1 W4A8 TTFT degradation (#8674) ...

### What this PR does / why we need it?
Fix TTFT degradation on Deepseek-V3.1-W4A8. Revert change of
`balance_flag` in https://github.com/vllm-project/vllm-ascend/pull/7611.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
- vLLM version: v0.18.0

Signed-off-by: Wangbingjie <wangbj1207@126.com>

2026-04-27 23:27:34 +08:00

..

_310p

[BugFix][310P][v0.18.0] Use CPU generator cache for sampling (#8624)

2026-04-24 09:34:14 +08:00

_cann_ops_custom

[Kernel] add custom op GmmSwigluQuantWeightNzTensorList (#3804)

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

attention

[BugFix][0.18.0] Fix quant_bias missing in w8a8_static when flashcomm1 is enabled for GLM-5 (#8304)

2026-04-17 22:46:36 +08:00

compilation

[v0.18.0][BugFix] PIECEWISE mode also requires synchronization (#8469)

2026-04-21 16:22:32 +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

[releases/v0.18.0][Doc][Misc] Modifying Configuration Parameters (#8618)

2026-04-23 16:23:31 +08:00

eplb

[V0.18.0][EPLB][BugFix] Fix moe_load precision in allgather (#7890)

2026-04-02 09:20:31 +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

[Bugfix][0.18.0] fix kernels in sample when mask is not static or draft_token_id is invalid (#8531)

2026-04-23 23:04:19 +08:00

patch

[v0.18.0][BugFix] Fix DSV3.1 W4A8 TTFT degradation (#8674)

2026-04-27 23:27:34 +08:00

quantization

[BugFix][0.18.0] Fix quant_bias missing in w8a8_static when flashcomm1 is enabled for GLM-5 (#8304)

2026-04-17 22:46:36 +08:00

sample

[releases/v0.18.0][Triton][Sampler] Add penalty-related Triton kernel for better performance of penalties (#7794)

2026-03-31 19:01:51 +08:00

spec_decode

[BugFix] fix hang in async scheduling while open ENPU (#8354)

2026-04-18 00:07:15 +08:00

worker

[v0.18.0][BugFix] Fix Qwen3.5 MoE FC1 error under high concurrency when dp>1 (#8395)

2026-04-20 10:26:19 +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

[BugFix][v0.18.0] Gate recompute/balance/fused_mc2 by PD mode (#8374)

2026-04-18 18:06:42 +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

[BugFix] Enforce C locale for CPU binding subprocess parsing (#8261)

2026-04-16 16:17:10 +08:00

envs.py

[BugFix]Backport validate pd mode feature gates no fused mc2 v0.18.0 clean (#8583)

2026-04-23 19:44:07 +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

[BugFix]Backport validate pd mode feature gates no fused mc2 v0.18.0 clean (#8583)

2026-04-23 19:44:07 +08:00

profiling_config.py

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

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

utils.py

[Performance] Use forward_native for Conv3dLayer and add UT (#8375)

2026-04-20 17:20:40 +08:00