yiz-liu 2c7dd85fd8 [Fix] Fix the token-wise padding mechanism (#1300) ...

### What this PR does / why we need it?
Fix the token-wise padding mechanism.

Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>

2025-06-20 14:46:17 +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 deepseek with mc2 (#1268)

2025-06-18 00:58:38 +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

static EPLB fix bug, add unit test (#1186)

2025-06-18 19:46:56 +08:00

sample

Spec decode support for V1 Engine (#874)

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

worker

[Fix] Fix the token-wise padding mechanism (#1300)

2025-06-20 14:46:17 +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

[Bugfix][Spec Decode] Enable ACL_OP_INIT_MODE=1 directly only when using V0 spec decode (#1258)

2025-06-18 17:50:20 +08:00

platform.py

[Bugfix][Spec Decode] Enable ACL_OP_INIT_MODE=1 directly only when using V0 spec decode (#1258)

2025-06-18 17:50:20 +08:00

utils.py

[refactor] Refactoring AscendFusedMoE (#1229)

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