text-generation-inference/backends/gaudi/server/text_generation_server/utils/kernels.py
Wang, Yi d62c941c56
Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)
* clean cuda/rocm code in hpu backend, enable flat_hpu

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* fix TP in pageattn

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* adjust block table in hpu to improve performance

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* enable all the model. not testet yet

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* use tensor cache in hpu graph to avoid replay issue

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* add moe support, fix qwen/mistral/mixtral crash

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* fix phimoe issue

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* gpt_bigcode could also go pageattn

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* enable dbrx remove some unused code

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* multi-modality initial PR

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* adjust warmup and enable vlm

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* fix incorrect output in qwen2 idefics if hpu graph is used

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* remove unused quantization code and enable awq/gptq int4

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* fix gptq issue

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* enable fp8

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* warmup prefill

remove model where pageattn is not used, set block table to None since it's not used

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* add warmup_decode

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* warmup decode

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* remove block_tables and prefill_cache_indices which will lead to dynamic shape

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* fix comment

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* missing gptj change...

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* fix some issue

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* remove torch.where to fix incorrect output in hpu graph model

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* match the latest vllm_extension ops

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

---------

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
2025-04-14 15:58:13 +02:00

23 lines
593 B
Python

import importlib
from loguru import logger
from hf_kernels import load_kernel as hf_load_kernel
from text_generation_server.utils.log import log_once
def load_kernel(*, module: str, repo_id: str):
"""
Load a kernel. First try to load it as the given module (e.g. for
local development), falling back to a locked Hub kernel.
"""
try:
m = importlib.import_module(module)
log_once(logger.info, f"Using local module for `{module}`")
return m
except ModuleNotFoundError:
return hf_load_kernel(repo_id=repo_id)
__all__ = ["load_kernel"]