AIbin fd91da7b41 【Inference Optimize】Support wint2 triton kernel about triton_utils_v2 (#2842) ...

* update supported_models doc

2025-07-15 14:35:40 +08:00

..

ops

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

__init__.py

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

block_wise_fp8.py

[Feature] block_wise_fp8 support triton_moe_backend (#2767)

2025-07-09 19:22:47 +08:00

kv_cache.py

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

mix_quant.py

[feat] support fa3 backend for pd disaggregated (#2695)

2025-07-03 22:33:27 +08:00

quant_base.py

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

tensor_wise_fp8.py

[Optimize] Optimize tensorwise fp8 performance (#2729)

2025-07-07 20:06:28 +08:00

w4a8.py

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

w4afp8.py

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

w8a8.py

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

weight_only.py

dcu adapter ernie45t (#2756)

2025-07-09 18:56:27 +08:00

wfp8afp8.py

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

wint2.py

【Inference Optimize】Support wint2 triton kernel about triton_utils_v2 (#2842)

2025-07-15 14:35:40 +08:00