mirror/OpenLLM
1
0
Fork 0
mirror of https://github.com/bentoml/OpenLLM.git synced 2026-04-23 08:28:24 -04:00
Code Issues Packages Projects Releases Wiki Activity

feat(client): support authentication token and shim implementation (#605)

Browse Source 
* chore: synch generate_iterator to be the same as server

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

* --wip--

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

* wip

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

* feat: cleanup shim implementation

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

* ci: auto fixes from pre-commit.ci

For more information, see https://pre-commit.ci

* chore: fix pre-commit

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

* chore: update changelog

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

* chore: update check with tuple

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

---------

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Aaron Pham
2023-11-10 17:44:31 -05:00
committed by GitHub
parent af0b1b9a7f
commit c41828f68f
25 changed files with 1086 additions and 344 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
openllm-python/src/openllm/serialisation/ggml.py
View File

@@ -1,30 +1,13 @@
"""Serialisation related implementation for GGML-based implementation.
This requires ctransformers to be installed.
"""
from __future__ import annotations
import typing as t
if t.TYPE_CHECKING:
import bentoml
import openllm
from openllm_core._typing_compat import M
_conversion_strategy = {'pt': 'ggml'}
def import_model(
llm: openllm.LLM[t.Any, t.Any], *decls: t.Any, trust_remote_code: bool = True, **attrs: t.Any
) -> bentoml.Model:
def import_model(llm, *decls, trust_remote_code=True, **attrs):
raise NotImplementedError('Currently work in progress.')
def get(llm: openllm.LLM[t.Any, t.Any]) -> bentoml.Model:
def get(llm):
raise NotImplementedError('Currently work in progress.')
def load_model(llm: openllm.LLM[M, t.Any], *decls: t.Any, **attrs: t.Any) -> M:
def load_model(llm, *decls, **attrs):
raise NotImplementedError('Currently work in progress.')

2
openllm-python/src/openllm/serialisation/transformers/__init__.py
View File

@@ -1,5 +1,3 @@
"""Serialisation related implementation for Transformers-based implementation."""
from __future__ import annotations
import importlib
import logging