Shengsheng Huang fd1061e7bf community[patch]: add more data types support to ipex-llm llm integration (#20833) ... - **Description**: - **add support for more data types**: by default `IpexLLM` will load the model in int4 format. This PR adds more data types support such as `sym_in5`, `sym_int8`, etc. Data formats like NF3, NF4, FP4 and FP8 are only supported on GPU and will be added in future PR. - Fix a small issue in saving/loading, update api docs - **Dependencies**: `ipex-llm` library - **Document**: In `docs/docs/integrations/llms/ipex_llm.ipynb`, added instructions for saving/loading low-bit model. - **Tests**: added new test cases to `libs/community/tests/integration_tests/llms/test_ipex_llm.py`, added config params. - **Contribution maintainer**: @shane-huang		2024-04-25 12:58:18 -07:00
..
grammars
__init__.py	community[minor]: Unify Titan Takeoff Integrations and Adding Embedding Support (#18775)	2024-04-17 01:43:35 +00:00
ai21.py
aleph_alpha.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
amazon_api_gateway.py
anthropic.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
anyscale.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
aphrodite.py
arcee.py
aviary.py
azureml_endpoint.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
baichuan.py
baidu_qianfan_endpoint.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
bananadev.py	community[patch]: introduce convert_to_secret() to bananadev llm (#14283)	2024-03-30 00:52:25 +00:00
baseten.py
beam.py
bedrock.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
bigdl_llm.py	community[patch]: add more data types support to ipex-llm llm integration (#20833)	2024-04-25 12:58:18 -07:00
bittensor.py
cerebriumai.py
chatglm3.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
chatglm.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
clarifai.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
cloudflare_workersai.py	community[patch]: docstrings update (#20301)	2024-04-11 16:23:27 -04:00
cohere.py	cohere[patch]: add cohere as a partner package (#19049)	2024-03-25 20:23:47 +00:00
ctransformers.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
ctranslate2.py
databricks.py	community[patch]: Databricks - fix scope of dangerous deserialization error in Databricks LLM connector (#20368)	2024-04-12 17:27:26 -04:00
deepinfra.py	community[patch]: Invoke callback prior to yielding token fix [DeepInfra] (#20427)	2024-04-14 14:32:52 -04:00
deepsparse.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
edenai.py	community[patch]: docstrings update (#20301)	2024-04-11 16:23:27 -04:00
fake.py
fireworks.py	community[patch]: invoke callback prior to yielding token (fireworks) (#19388)	2024-03-22 16:44:06 -07:00
forefrontai.py
friendli.py	community[minor]: Integration for Friendli LLM and ChatFriendli ChatModel. (#17913)	2024-03-08 02:20:47 +00:00
gigachat.py	community[minor]: Added GigaChat Embeddings support + updated previous GigaChat integration (#19516)	2024-03-25 16:08:37 -07:00
google_palm.py
gooseai.py
gpt4all.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
gradient_ai.py
huggingface_endpoint.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
huggingface_hub.py
huggingface_pipeline.py	docs: Update docs for HuggingFacePipeline (#19306)	2024-03-25 00:29:21 -07:00
huggingface_text_gen_inference.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
human.py	community[patch]: docstrings update (#20301)	2024-04-11 16:23:27 -04:00
ipex_llm.py	community[patch]: add more data types support to ipex-llm llm integration (#20833)	2024-04-25 12:58:18 -07:00
javelin_ai_gateway.py
koboldai.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
konko.py	community[patch]: docstrings update (#20301)	2024-04-11 16:23:27 -04:00
layerup_security.py	community[patch]: docstrings update (#20301)	2024-04-11 16:23:27 -04:00
llamacpp.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
llamafile.py	core, openai: support custom token encoders (#20762)	2024-04-23 13:57:05 +00:00
loading.py	community[patch]: docstrings update (#20301)	2024-04-11 16:23:27 -04:00
manifest.py
minimax.py
mlflow_ai_gateway.py	community[patch]: docstrings update (#20301)	2024-04-11 16:23:27 -04:00
mlflow.py	community[patch]: docstrings update (#20301)	2024-04-11 16:23:27 -04:00
mlx_pipeline.py	community[minor]: Add support for MLX models (chat & llm) (#18152)	2024-04-09 14:17:07 +00:00
modal.py
moonshot.py	community[patch]: docstrings update (#20301)	2024-04-11 16:23:27 -04:00
mosaicml.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
nlpcloud.py
oci_data_science_model_deployment_endpoint.py
oci_generative_ai.py
octoai_endpoint.py	community[patch]: update OctoAI endpoint to subclass BaseOpenAI (#19757)	2024-04-16 17:32:20 -07:00
ollama.py	community[patch]: Fix Ollama for LLaMA3 (#20624)	2024-04-19 00:20:32 +00:00
opaqueprompts.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
openai.py	community[patch]: invoke callback prior to yielding token (openai) (#19389)	2024-03-22 16:45:55 -07:00
openllm.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
openlm.py
pai_eas_endpoint.py	community[patch]: Invoke callback prior to yielding token (pai_eas_endpoint) (#18627)	2024-03-20 07:56:58 -07:00
petals.py
pipelineai.py
predibase.py	community: Support both Predibase SDK-v1 and SDK-v2 in Predibase-LangChain integration (#20859)	2024-04-24 13:31:01 -07:00
predictionguard.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
promptlayer_openai.py	community[patch]: docstrings update (#20301)	2024-04-11 16:23:27 -04:00
replicate.py	community: update Replicate to work with official models (#20633)	2024-04-19 01:43:40 +00:00
rwkv.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
sagemaker_endpoint.py	community[patch]: docstrings update (#20301)	2024-04-11 16:23:27 -04:00
self_hosted_hugging_face.py
self_hosted.py	community[major]: breaking change in some APIs to force users to opt-in for pickling (#18696)	2024-03-06 16:43:01 -05:00
solar.py	upstage: init package (#20574)	2024-04-17 23:25:36 +00:00
sparkllm.py	community[patch]: docstrings update (#20301)	2024-04-11 16:23:27 -04:00
stochasticai.py
symblai_nebula.py
textgen.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
titan_takeoff.py	community[minor]: Unify Titan Takeoff Integrations and Adding Embedding Support (#18775)	2024-04-17 01:43:35 +00:00
together.py
tongyi.py	community[patch]: Fixed bug in merging generation_info during chunk concatenation in Tongyi and ChatTongyi (#19014)	2024-03-15 16:27:53 -07:00
utils.py
vertexai.py	community[patch]: docstrings update (#20301)	2024-04-11 16:23:27 -04:00
vllm.py
volcengine_maas.py
watsonxllm.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
weight_only_quantization.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
writer.py
xinference.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00
yandex.py	community[patch]: YandexGPT API add ability to disable request logging (#20670)	2024-04-19 21:40:37 -04:00
yuan2.py	patch: remove usage of llm, chat model __call__ (#20788)	2024-04-24 19:39:23 -04:00