mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-19 22:02:06 +00:00
* 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>
23 lines
593 B
Python
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"]
|