mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-24 00:12:08 +00:00
d62c941c56
* 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>
25 lines
552 B
Python
25 lines
552 B
Python
from typing import Optional
|
|
|
|
SUPPORT_CHUNKING: Optional[bool] = None
|
|
MAX_PREFILL_TOKENS: Optional[int] = None
|
|
|
|
|
|
def set_support_chunking(support_chunking: bool):
|
|
global SUPPORT_CHUNKING
|
|
SUPPORT_CHUNKING = support_chunking
|
|
|
|
|
|
def get_support_chunking() -> bool:
|
|
global SUPPORT_CHUNKING
|
|
return SUPPORT_CHUNKING
|
|
|
|
|
|
def set_max_prefill_tokens(max_prefill_tokens: int):
|
|
global MAX_PREFILL_TOKENS
|
|
MAX_PREFILL_TOKENS = max_prefill_tokens
|
|
|
|
|
|
def get_max_prefill_tokens() -> int:
|
|
global MAX_PREFILL_TOKENS
|
|
return MAX_PREFILL_TOKENS
|