LI SHENGYONG bc1f6713e7 [EPLB][Bugfix] Dispatch Allgather use log2phy if enable eplb (#5933) ...

### What this PR does / why we need it?
1. Move the logic of expert mapping forward to prevent shotgun changes
2. Disable the update of expert map.

### How was this patch tested?
a2
| dataset | version | metric | mode | vllm-api-general-chat |
|----- | ----- | ----- | ----- | -----|
| GPQA_diamond | 53064e | accuracy | gen | 73.23 |

a3
| dataset | version | metric | mode | vllm-api-general-chat |
|----- | ----- | ----- | ----- | -----|
| aime2024 | 604a78 | accuracy | gen | 83.33 |


- vLLM version: v0.13.0
- vLLM main:
11b6af5280

Signed-off-by: shenchuxiaofugui <1311027364@qq.com>

2026-01-19 09:24:25 +08:00

..

_310p

[Feature]: Support 310P device run qwen2.5/3 dense and qwen2.5vl models (#5776)

2026-01-17 11:49:18 +08:00

_cann_ops_custom

[Kernel] add custom op GmmSwigluQuantWeightNzTensorList (#3804)

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

attention

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

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

compilation

Revert "[bugfix]limit graph replay sync (#5761)" (#5965)

2026-01-16 23:29:35 +08:00

core

[CI] fix lint (#5216)

2025-12-20 17:03:25 +08:00

device

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

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

device_allocator

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

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

distributed

[P/D]The issue of solving the force-free secondary release request, which causes the node to crash. (#5968)

2026-01-17 18:49:27 +08:00

eplb

[EPLB][Bugfix] Dispatch Allgather use log2phy if enable eplb (#5933)

2026-01-19 09:24:25 +08:00

kv_offload

[Main2Main] Upgrade vllm commit to 0113 (#5839)

2026-01-15 09:48:53 +08:00

lora

[BufFix]Fix the error when using Ascend custom operators with rank=128 (#5394)

2026-01-09 15:57:43 +08:00

model_loader

[BugFix] NetLoader: No backend type associated with device type npu (#5700)

2026-01-09 15:54:54 +08:00

ops

[EPLB][Bugfix] Dispatch Allgather use log2phy if enable eplb (#5933)

2026-01-19 09:24:25 +08:00

patch

[Feature]: Support 310P device run qwen2.5/3 dense and qwen2.5vl models (#5776)

2026-01-17 11:49:18 +08:00

quantization

[Feature] Support fine-grained shared expert overlap (#5482)

2026-01-17 11:53:22 +08:00

sample

[Feature] add the magicmtp speculative decoding acceleration algorithm (#5542)

2026-01-08 09:15:55 +08:00

spec_decode

Eagle3 mm support, enablement on qwen3vl (#4848)

2026-01-19 08:58:07 +08:00

worker

Eagle3 mm support, enablement on qwen3vl (#4848)

2026-01-19 08:58:07 +08:00

xlite

[BugFix] Xlite: Bypass the padding of the graph mode in non-MTP cases to obtain the correct decode num. (#5711)

2026-01-09 15:55:30 +08:00

__init__.py

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

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

ascend_config.py

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

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

ascend_forward_context.py

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

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

batch_invariant.py

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

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

cpu_binding.py

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

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

envs.py

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

2026-01-19 08:59:46 +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

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

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

platform.py

[Bugfix][MM] Fix multi-modal inference OOM issues by setting expandable_segments:True (#5855)

2026-01-19 09:17:31 +08:00

profiling_config.py

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

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

utils.py

[Feature]: Support 310P device run qwen2.5/3 dense and qwen2.5vl models (#5776)

2026-01-17 11:49:18 +08:00