Pleaplusone 38f34e359f [Fix] fix deepseek v0 attention eager mode (#671) ...

### What this PR does / why we need it?
`reshape_and_cache_siso` seems have some funcitonality issues, use torch
op combination replace this custom op by default.


---------

Signed-off-by: ganyi <pleaplusone.gy@gmail.com>

2025-04-28 08:53:06 +08:00

..

attention

[Fix] fix deepseek v0 attention eager mode (#671)

2025-04-28 08:53:06 +08:00

core

[BUGFIX] main-sd-bugfix && [UT] add mtp UT (#593)

2025-04-21 19:25:51 +08:00

device_allocator

catch ImportError when C code not compiled (#575)

2025-04-18 18:11:49 +08:00

distributed

[BUGFIX] main-sd-bugfix && [UT] add mtp UT (#593)

2025-04-21 19:25:51 +08:00

lora

[Bugfix] fix import error (#600)

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

models

[BUILD] Upgrade torch-npu to 2.5.1 (#661)

2025-04-27 17:28:29 +08:00

ops

support aclgraph (#426)

2025-04-23 20:56:24 +08:00

patch

[Model][MiniCPM] support MiniCPM (#645)

2025-04-27 11:27:24 +08:00

quantization

support deepseek quant & mix-parallel with graphmode (#585)

2025-04-23 16:23:25 +08:00

worker

Remove prompt string from engine core data structures (#663)

2025-04-26 23:15:58 +08:00

__init__.py

Add sleep mode feature for Ascend NPU (#513)

2025-04-18 13:11:39 +08:00

envs.py

Add sleep mode feature for Ascend NPU (#513)

2025-04-18 13:11:39 +08:00

platform.py

[V1] Make V1 engine backward compatible (#637)

2025-04-24 17:20:11 +08:00

utils.py

support deepseek quant & mix-parallel with graphmode (#585)

2025-04-23 16:23:25 +08:00