TJian f5a3c655b2 [FEAT] [ROCm]: Add Qwen/Qwen3-235B-A22B-FP8 TP4 triton fused moe config (#17535) ...

Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>

2025-05-01 06:37:17 -07:00

..

configs

[FEAT] [ROCm]: Add Qwen/Qwen3-235B-A22B-FP8 TP4 triton fused moe config (#17535)

2025-05-01 06:37:17 -07:00

__init__.py

[Minor] Fused experts refactor (#15914)

2025-04-03 10:19:38 -07:00

cutlass_moe.py

[Kernel] Add expert_map support to Cutlass FP8 MOE (#16861)

2025-04-21 20:44:32 -07:00

deep_gemm_moe.py

[Minor] Fused experts refactor (#15914)

2025-04-03 10:19:38 -07:00

fused_marlin_moe.py

[Kernel] moe wna16 marlin kernel (#14447)

2025-04-14 20:05:22 -07:00

fused_moe.py

[ROCm] Add aiter tkw1 kernel for Llama4 fp8 (#16727)

2025-04-21 20:42:34 -07:00

layer.py

[Bugfix] Fix moe weight losing all extra attrs after process_weights_after_loading. (#16854)

2025-04-28 21:05:07 +00:00

moe_align_block_size.py

[Minor] Fused experts refactor (#15914)

2025-04-03 10:19:38 -07:00

moe_pallas.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

moe_torch_iterative.py

Expert Parallelism (EP) Support for DeepSeek V2 (#12583)

2025-02-24 07:33:20 -08:00

rocm_aiter_fused_moe.py

[FEAT] [ROCm]: AITER Fused MOE V1 Support (#16752)

2025-04-25 11:06:50 +08:00

utils.py

[Minor] Fused experts refactor (#15914)

2025-04-03 10:19:38 -07:00