Xinyu Dong 07bc24a555 [Bugs] Fix moe when without bias (#76)

2026-01-05 10:51:23 +08:00

..

attention

提交vllm0.11.0开发分支

2025-12-10 17:51:24 +08:00

fla

[Kernel] Qwen3-next 优化 recompute_w_u_fwd & chunk_fwd_o (#74)

2026-01-05 10:24:51 +08:00

fused_moe

[Bugs] Fix moe when without bias (#76)

2026-01-05 10:51:23 +08:00

mamba

[Kernel] Optimize the performance of causal_conv1d.

2025-12-12 17:22:35 +08:00

quantization

[dev] support AWQ/GPTQ quantization for dense models

2025-12-24 13:46:06 +08:00

sample

提交vllm0.11.0开发分支

2025-12-10 17:51:24 +08:00

__init__.py

remove qwen2.py llama.py fix llama output

2025-12-31 11:39:37 +08:00

_kunlun_ops.py

[Feature] Support gpt-oss and update model list (#71)

2026-01-04 21:19:49 +08:00

activation.py

remove qwen2.py llama.py fix llama output

2025-12-31 11:39:37 +08:00

layernorm.py

[Feature] Support XiaoMi MIMO Flash V2 (#62)

2025-12-31 10:16:33 +08:00

linear.py

[Feature] Support XiaoMi MIMO Flash V2 (#62)

2025-12-31 10:16:33 +08:00

paged_attn.py

[Feature] Support XiaoMi MIMO Flash V2 (#62)

2025-12-31 10:16:33 +08:00

rotary_embedding.py

[Feature] Support gpt-oss and update model list (#71)

2026-01-04 21:19:49 +08:00

vocab_parallel_embedding.py

[Feature] Support XiaoMi MIMO Flash V2 (#62)

2025-12-31 10:16:33 +08:00