fmiao2372 404cf0ece4 [Intel HPU] enable tensor_wise_fp8 (#5324) ...

* [Intel HPU] enable tensor_wise_fp8

* update code based on comments

* fix code style issue

* fix bug about RP 5138

* mv kv_cache modifications to HPU backend

* fix FP8 Precision Issues

* fix FP8 Precision Issues

* Add quantization UT

---------

Co-authored-by: yanfeich <yanfei.cheng@intel.com>
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>

2025-12-17 16:45:03 +08:00

..

__init__.py

[Intel HPU] Support intel hpu platform (#4161)

2025-09-24 12:27:50 +08:00

base.py

[Feature] support flash_mask_attention backend (#5134)

2025-11-28 10:12:16 +08:00

cpu.py

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

cuda.py

[Feature] support flash_mask_attention backend (#5134)

2025-11-28 10:12:16 +08:00

dcu.py

add error traceback info (#3419)

2025-08-19 19:32:04 +08:00

gcu.py

add error traceback info (#3419)

2025-08-19 19:32:04 +08:00

iluvatar.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

intel_hpu.py

[Intel HPU] enable tensor_wise_fp8 (#5324)

2025-12-17 16:45:03 +08:00

maca.py

[Metax] adapt DeepSeek (#4498)

2025-10-24 10:14:53 +08:00

npu.py

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

utils.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

xpu.py

add error traceback info (#3419)

2025-08-19 19:32:04 +08:00