Shiwen Tang 8988ad08b2 [Feature] Support Mixed-Precision Quantization for MoE (#112)

2026-01-14 18:42:18 +08:00

..

attention

[Feature] support deepseek v3/r1/v3.2 (#78)

2026-01-05 22:55:35 +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

[Feature] Support Mixed-Precision Quantization for MoE (#112)

2026-01-14 18:42:18 +08:00

mamba

[Kernel] Optimize the performance of causal_conv1d.

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

quantization

[Bugfix] fix can not import compressed_tensors (#87)

2026-01-07 11:32:10 +08:00

sample

提交vllm0.11.0开发分支

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

__init__.py

[fix]update compressed-tensors scheme

2026-01-06 22:30:27 +08:00

_kunlun_ops.py

[Feature] support deepseek v3/r1/v3.2 (#78)

2026-01-05 22:55:35 +08:00

activation.py

[Feature] support deepseek v3/r1/v3.2 (#78)

2026-01-05 22:55:35 +08:00

deep_gemm.py

[Feature] support deepseek v3/r1/v3.2 (#78)

2026-01-05 22:55:35 +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 deepseek v3/r1/v3.2 (#78)

2026-01-05 22:55:35 +08:00

vocab_parallel_embedding.py

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

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