whx d7e19ed57a [BugFix] fix length of sin/cos cache in rope (#1266) ...

This PR fixes the bug that constructs shorter sin/cos cache than model's
max positional embedding.

Closes: https://github.com/vllm-project/vllm-ascend/issues/1038

Signed-off-by: whx-sjtu <2952154980@qq.com>

2025-06-17 23:14:25 +08:00

..

attention

[refactor] Refactoring AscendFusedMoE (#1229)

2025-06-17 17:49:03 +08:00

compilation

[CI] Upgrade vllm to 0.9.1 (#1165)

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

core

[Scheduler][MTP] Add support for speculative decoding in AsecendScheduler. (#943)

2025-06-11 20:55:44 +08:00

device_allocator

[Bugfix] Remove cuda related lines and add additional pip mirror (#1252)

2025-06-17 21:25:40 +08:00

distributed

[bugfix] some bugs maybe fail to run (#896)

2025-06-03 11:07:33 +08:00

lora

[Bugfix] fix import error (#600)

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

models

[refactor] Refactoring AscendFusedMoE (#1229)

2025-06-17 17:49:03 +08:00

multistream

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

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

ops

[BugFix] fix length of sin/cos cache in rope (#1266)

2025-06-17 23:14:25 +08:00

patch

[DP][V1] Fix rank set in DP scenario & Bump torch-npu version to 2.5.1.post1.dev20250528 (#1235)

2025-06-16 23:09:53 +08:00

quantization

[Bugfix]: Pass scaling args to mc2 (#1202)

2025-06-17 22:16:44 +08:00

sample

Spec decode support for V1 Engine (#874)

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

worker

[refactor] Refactoring AscendFusedMoE (#1229)

2025-06-17 17:49:03 +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] Add unit test framework (#1201)

2025-06-16 18:32:28 +08:00

envs.py

[refactor] Refactoring AscendFusedMoE (#1229)

2025-06-17 17:49:03 +08:00

platform.py

Fix the device error when using ray as vllm-acend backend (#884)

2025-06-16 21:03:16 +08:00

utils.py

[refactor] Refactoring AscendFusedMoE (#1229)

2025-06-17 17:49:03 +08:00