mirror/OpenLLM
1
0
Fork 0
mirror of https://github.com/bentoml/OpenLLM.git synced 2026-03-07 08:38:20 -05:00
Code Issues Packages Projects Releases Wiki Activity

fix(serialisation): vLLM safetensors support (#324)

Browse Source 
* fix(serilisation): vllm support for safetensors

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>

* chore: running tools

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* chore: generalize one shot generation

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* chore: add changelog [skip ci]

Signed-off-by: paperspace <29749331+aarnphm@users.noreply.github.com>

---------

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
Signed-off-by: paperspace <29749331+aarnphm@users.noreply.github.com>
This commit is contained in:
Aaron Pham
2023-09-12 17:44:01 -04:00
committed by GitHub
parent c70d4edcb1
commit 35e6945e86
11 changed files with 29 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
openllm-python/src/openllm/utils/dummy_pt_objects.py generated
View File

@@ -19,8 +19,8 @@ class GPTNeoX(metaclass=_DummyMetaclass):
_backends=["torch"]
def __init__(self,*param_decls:_t.Any,**attrs: _t.Any):_require_backends(self,["torch"])
class Llama(metaclass=_DummyMetaclass):
_backends=["torch","fairscale","sentencepiece"]
def __init__(self,*param_decls:_t.Any,**attrs: _t.Any):_require_backends(self,["torch","fairscale","sentencepiece"])
_backends=["torch","fairscale","sentencepiece","scipy"]
def __init__(self,*param_decls:_t.Any,**attrs: _t.Any):_require_backends(self,["torch","fairscale","sentencepiece","scipy"])
class MPT(metaclass=_DummyMetaclass):
_backends=["torch","triton","einops"]
def __init__(self,*param_decls:_t.Any,**attrs: _t.Any):_require_backends(self,["torch","triton","einops"])

4
openllm-python/src/openllm/utils/dummy_vllm_objects.py generated
View File

@@ -28,8 +28,8 @@ class VLLMStarCoder(metaclass=_DummyMetaclass):
_backends=["vllm","bitsandbytes"]
def __init__(self,*param_decls:_t.Any,**attrs: _t.Any):_require_backends(self,["vllm","bitsandbytes"])
class VLLMLlama(metaclass=_DummyMetaclass):
_backends=["vllm","fairscale","sentencepiece"]
def __init__(self,*param_decls:_t.Any,**attrs: _t.Any):_require_backends(self,["vllm","fairscale","sentencepiece"])
_backends=["vllm","fairscale","sentencepiece","scipy"]
def __init__(self,*param_decls:_t.Any,**attrs: _t.Any):_require_backends(self,["vllm","fairscale","sentencepiece","scipy"])
class AutoVLLM(metaclass=_DummyMetaclass):
_backends=["vllm"]
def __init__(self,*param_decls:_t.Any,**attrs: _t.Any):_require_backends(self,["vllm"])