ChrisGelhLan 5ebb9bd8d2 【Bugfix】bugfix_for_bmm_transpose (#4899) ...

The bmm_transpose operator in version 3.2 is only used in the decoding stage due to shape limitations.

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: ChrisGelhLan <33011886+xlan-huawei@users.noreply.github.com>

2025-12-11 16:32:28 +08:00

..

_cann_ops_custom

[Kernel] add custom op GmmSwigluQuantWeightNzTensorList (#3804)

2025-11-28 18:06:39 +08:00

attention

【Bugfix】bugfix_for_bmm_transpose (#4899)

2025-12-11 16:32:28 +08:00

compilation

[Feature] Support npuhraph_ex backend (#4700)

2025-12-10 20:48:05 +08:00

core

Drop ascend scheduler (#4623)

2025-12-05 09:03:45 +08:00

device_allocator

[Misc]Clean up useless import from vllm (#2049)

2025-07-28 16:01:59 +08:00

distributed

[Feat] Flashcomm2 use o_shared linear (#4188)

2025-12-11 12:43:04 +08:00

eplb

[Feat] Multi-stream for eplb heat collection and aggregation (#4214)

2025-12-09 16:16:55 +08:00

kv_offload

upgrade vLLM to main (#4608)

2025-12-02 22:10:52 +08:00

lora

[refact] unified soc_version code (#4359)

2025-11-26 14:28:55 +08:00

model_loader

Drop 0.11.0 support (#4377)

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

ops

[OPS] support triton causal_conv1d_fn ops (#4119)

2025-12-11 15:52:39 +08:00

patch

[OPS] support triton causal_conv1d_fn ops (#4119)

2025-12-11 15:52:39 +08:00

quantization

[Feat] Support native Kimi-K2-Thinking native W4A16 quantized experts weights (#4516)

2025-12-10 15:58:52 +08:00

sample

Fixed the performance degradation issue in post-processing in speculative decoding scenarios. (#4849)

2025-12-10 20:32:44 +08:00

spec_decode

cleanup useless torchair logic (#4856)

2025-12-11 11:21:13 +08:00

worker

cleanup useless torchair logic (#4856)

2025-12-11 11:21:13 +08:00

xlite

[Feat] Add Euler xlite graph wrapper support (#4526)

2025-12-08 08:27:46 +08:00

__init__.py

clean up model module (#4611)

2025-12-02 17:35:47 +08:00

ascend_config.py

[Feat] Flashcomm2 use o_shared linear (#4188)

2025-12-11 12:43:04 +08:00

ascend_forward_context.py

add dispatch_gmm_combine kernel (#3532)

2025-12-04 23:00:59 +08:00

cpu_binding.py

[main] support cpu binding (#3546)

2025-10-21 09:17:03 +08:00

envs.py

[Feat] Flashcomm2 use o_shared linear (#4188)

2025-12-11 12:43:04 +08:00

meta_registration.py

Fix the bugs about operator registration by PyTorch Dispatcher (#2786)

2025-09-13 11:58:52 +08:00

platform.py

cleanup useless torchair logic (#4856)

2025-12-11 11:21:13 +08:00

profiling_config.py

Drop ascend scheduler (#4623)

2025-12-05 09:03:45 +08:00

utils.py

[Feat] Flashcomm2 use o_shared linear (#4188)

2025-12-11 12:43:04 +08:00