RuohengMa de0c5e68fb [XPU] Split the block_attn operator into smaller operators (#6798) ...

* spliced block_attn

* adapt to latest vllm

* fix unit tests

* delete mtp+cudagraph 4 cards test

* fix vl model

* fix mtp

* fix slot mapping

2026-04-16 14:28:40 +08:00

..

graph_optimization

[RL] Add clear_graph_opt_backend for glm4_mtp (#7378)

2026-04-15 19:44:15 +08:00

guided_decoding

[Optimization] Use a separate driver when using Triton with Paddle (#6897)

2026-03-24 10:56:00 +08:00

layers

[XPU] Split the block_attn operator into smaller operators (#6798)

2026-04-16 14:28:40 +08:00

logits_processor

[Bugfix] Align thinking_budget behavior with ERNIE reasoning flow (#6934)

2026-03-23 14:15:55 +08:00

model_loader

[Loader] add multi-thread model loading (#6877)

2026-04-09 23:40:15 -07:00

models

[Optimization] enable trtllm_all_reduce fusion kernel in glm model (#6660)

2026-04-16 14:10:19 +08:00

ops

[Others] Fix typo (#7280)

2026-04-14 17:28:22 +08:00

__init__.py

…

entropy_utils.py

[Bugfix] Fix entropy calculation bugs (#5941)

2026-01-08 20:57:35 +08:00

forward_meta.py

[XPU] Split the block_attn operator into smaller operators (#6798)

2026-04-16 14:28:40 +08:00

load_weight_utils.py

[Loader] add multi-thread model loading (#6877)

2026-04-09 23:40:15 -07:00

pre_and_post_process.py

[Speculative Decoding] Support mtp super ultra overlap in pd-split mode with insert_task overlap (#7323)

2026-04-13 19:41:17 +08:00

utils.py

[Optimization] enable trtllm_all_reduce fusion kernel in glm model (#6660)

2026-04-16 14:10:19 +08:00

xpu_pre_and_post_process.py

[XPU] Split the block_attn operator into smaller operators (#6798)

2026-04-16 14:28:40 +08:00