GoldPancake f7cad30a38 [Feature] Add speculative decoding simulation benchmark. (#2751) ...

* Add speculative decoding simulation benchmark

* Fix the name of the parameter

2025-07-09 12:08:43 +08:00

..

attention

Revert "[Bug fix] fix attention rank init (#2743)" (#2761)

2025-07-09 10:38:12 +08:00

backends

[GCU] Support gcu platform (#2702)

2025-07-08 13:00:52 +08:00

moe

[GCU] Support gcu platform (#2702)

2025-07-08 13:00:52 +08:00

quantization

[GCU] Support gcu platform (#2702)

2025-07-08 13:00:52 +08:00

sample

[Feature] Add speculative decoding simulation benchmark. (#2751)

2025-07-09 12:08:43 +08:00

__init__.py

…

activation.py

[GCU] Support gcu platform (#2702)

2025-07-08 13:00:52 +08:00

embeddings.py

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

hydra_head.py

…

linear.py

[GCU] Support gcu platform (#2702)

2025-07-08 13:00:52 +08:00

lm_head.py

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

mtp_linear.py

Extract eh_proj Layer from ParallelLMHead for MTP to Avoid Weight Transposition Issue (#2707)

2025-07-04 14:15:04 +08:00

normalization.py

[GCU] Support gcu platform (#2702)

2025-07-08 13:00:52 +08:00

rotary_embedding.py

[GCU] Support gcu platform (#2702)

2025-07-08 13:00:52 +08:00

utils.py

Adapt for iluvatar gpu (#2684)

2025-07-07 16:53:14 +08:00