Zetong Li 4fa7cf6f50 [Bugfix] Fix problematic dummy_run & improper input_batch_size in eagle (#6517) ...

### What this PR does / why we need it?
This PR aims to fix problematic dummy_run that will cause excessive npu
memory and to fix improper input_batch_size that will degrade running
performance.

### Does this PR introduce _any_ user-facing change?
N/A

### How was this patch tested?
by ci

- vLLM version: v0.15.0
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.15.0

---------

Signed-off-by: Zetong Li <slippersss@126.com>
Signed-off-by: lilinsiman <lilinsiman@gmail.com>
Co-authored-by: lilinsiman <lilinsiman@gmail.com>

2026-02-07 09:30:10 +08:00

..

_310p

[Refactor]310p_e2e test case update (#6539)

2026-02-07 09:28:37 +08:00

_cann_ops_custom

[Kernel] add custom op GmmSwigluQuantWeightNzTensorList (#3804)

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

attention

[Bugfix] Fix the incorrect use of the output parameter in _forward_fia_slidingwindow (#6469)

2026-02-05 20:58:54 +08:00

compilation

[main2main] upgrade vllm main 0202 (#6560)

2026-02-05 19:31:17 +08:00

core

[0.14.1][bugfix][sched] fix incompatibility of RecomputeScheduler with vllm v0.14.1 (#6286)

2026-01-28 20:16:58 +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

[Refactor]refactor p2p connector (#6551)

2026-02-07 09:27:15 +08:00

eplb

[EPLB][Bugfix] EPLB support fp/bf16 (#5531)

2026-01-26 14:28:16 +08:00

kv_offload

[main2main] upgrade vllm main 0202 (#6560)

2026-02-05 19:31:17 +08:00

lora

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #5) (#5996)

2026-01-24 22:45:38 +08:00

model_loader

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #6) (#6001)

2026-01-24 22:08:33 +08:00

ops

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

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

patch

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #10) (#6173)

2026-02-06 15:35:06 +08:00

quantization

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #7) (#6023)

2026-02-06 14:56:53 +08:00

sample

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #7) (#6023)

2026-02-06 14:56:53 +08:00

spec_decode

[Bugfix] Fix problematic dummy_run & improper input_batch_size in eagle (#6517)

2026-02-07 09:30:10 +08:00

worker

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #10) (#6173)

2026-02-06 15:35:06 +08:00

xlite

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #10) (#6173)

2026-02-06 15:35:06 +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

[Refactor] MLP weight prefetch to consistency with MoE Model's prefetching in terms of code and usage (#6442)

2026-02-04 09:08:18 +08:00

ascend_forward_context.py

[Feat.]: 310p support MOE models (#6530)

2026-02-06 10:30:56 +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

[CI] Update UT CANN version to 8.5.0 for main branch (#6564)

2026-02-06 10:28:42 +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 310p w8a8 (#6454)

2026-02-03 14:13:06 +08:00

profiling_config.py

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

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

utils.py

[Feat.]: 310p support MOE models (#6530)

2026-02-06 10:30:56 +08:00