llama 3.1 support (#1586)

montanalow · web-flow · commit 76ed53709604 · 2024-07-23T18:00:33.000-07:00
diff --git a/.github/workflows/ubuntu-packages-and-docker-image.yml b/.github/workflows/ubuntu-packages-and-docker-image.yml
@@ -4,7 +4,7 @@ on:
   workflow_dispatch:
     inputs:
       packageVersion:
-        default: "2.9.2"
+        default: "2.9.3"
 jobs:
   #
   # PostgresML extension.
diff --git a/pgml-cms/docs/open-source/pgml/developers/contributing.md b/pgml-cms/docs/open-source/pgml/developers/contributing.md
@@ -127,7 +127,7 @@ SELECT pgml.version();
 postgres=# select pgml.version();
       version
 -------------------
- 2.9.2
+ 2.9.3
 (1 row)
 ```
 {% endtab %}
diff --git a/pgml-cms/docs/open-source/pgml/developers/installation.md b/pgml-cms/docs/open-source/pgml/developers/installation.md
@@ -132,7 +132,7 @@ CREATE EXTENSION
 pgml_test=# SELECT pgml.version();
  version 
 ---------
- 2.9.2
+ 2.9.3
 (1 row)
 ```
 
diff --git a/pgml-cms/docs/open-source/pgml/developers/quick-start-with-docker.md b/pgml-cms/docs/open-source/pgml/developers/quick-start-with-docker.md
@@ -18,7 +18,7 @@ docker run \
     -v postgresml_data:/var/lib/postgresql \
     -p 5433:5432 \
     -p 8000:8000 \
-    ghcr.io/postgresml/postgresml:2.9.2 \
+    ghcr.io/postgresml/postgresml:2.9.3 \
     sudo -u postgresml psql -d postgresml
 ```
 {% endtab %}
@@ -43,7 +43,7 @@ docker run \
     --gpus all \
     -p 5433:5432 \
     -p 8000:8000 \
-    ghcr.io/postgresml/postgresml:2.9.2 \
+    ghcr.io/postgresml/postgresml:2.9.3 \
     sudo -u postgresml psql -d postgresml
 ```
 
@@ -80,7 +80,7 @@ Time: 41.520 ms
 postgresml=# SELECT pgml.version();
  version 
 ---------
- 2.9.2
+ 2.9.3
 (1 row)
 ```
 
diff --git a/pgml-cms/docs/open-source/pgml/developers/self-hosting/pooler.md b/pgml-cms/docs/open-source/pgml/developers/self-hosting/pooler.md
@@ -115,6 +115,6 @@ Type "help" for help.
 postgresml=> SELECT pgml.version();
  version
 ---------
- 2.9.2
+ 2.9.3
 (1 row)
 ```
diff --git a/pgml-extension/Cargo.lock b/pgml-extension/Cargo.lock
diff --git a/pgml-extension/Cargo.toml b/pgml-extension/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "pgml"
-version = "2.9.2"
+version = "2.9.3"
 edition = "2021"
 
 [lib]
diff --git a/pgml-extension/examples/transformers.sql b/pgml-extension/examples/transformers.sql
@@ -8,16 +8,14 @@ SELECT pgml.embed('Alibaba-NLP/gte-base-en-v1.5', 'hi mom', '{"device": "cpu"}')
 SELECT pgml.embed('hkunlp/instructor-xl', 'hi mom', '{"instruction": "Encode it with love"}');
 SELECT pgml.embed('mixedbread-ai/mxbai-embed-large-v1', 'test', '{"prompt": "test prompt: "}');
 
-SELECT pgml.transform_stream(
+SELECT pgml.transform(
   task   => '{
     "task": "text-generation",
     "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
-    "model_type": "mistral",
-    "revision": "main",
-    "device_map": "auto",
-    "token": "hf_123"
+    "token": "hf_123",
+    "trust_remote_code": true
   }'::JSONB,
-  input => 'AI is going to',
+  inputs => ARRAY['AI is going to'],
   args   => '{
     "max_new_tokens": 100
   }'::JSONB
diff --git a/pgml-extension/requirements.linux.txt b/pgml-extension/requirements.linux.txt
@@ -1,84 +1,78 @@
-accelerate==0.30.1
+accelerate==0.33.0
 aiohttp==3.9.5
 aiosignal==1.3.1
-annotated-types==0.6.0
-anyio==4.3.0
+annotated-types==0.7.0
+anyio==4.4.0
 async-timeout==4.0.3
 attrs==23.2.0
 auto_gptq==0.7.1
-bitsandbytes==0.43.1
+bitsandbytes==0.43.2
 catboost==1.2.5
-certifi==2024.2.2
+certifi==2024.7.4
 charset-normalizer==3.3.2
 click==8.1.7
 cloudpickle==3.0.0
-cmake==3.29.2
+cmake==3.30.1
 colorama==0.4.6
-coloredlogs==15.0.1
 contourpy==1.2.1
 ctransformers==0.2.27
 cycler==0.12.1
-dataclasses-json==0.6.6
 datasets==2.16.1
-deepspeed==0.14.2
+deepspeed==0.14.4
 dill==0.3.7
 diskcache==5.6.3
 distro==1.9.0
 dnspython==2.6.1
 docstring_parser==0.16
 einops==0.8.0
-email_validator==2.1.1
+email_validator==2.2.0
 evaluate==0.4.2
-exceptiongroup==1.2.1
-fastapi==0.111.0
-fastapi-cli==0.0.3
-filelock==3.14.0
-fonttools==4.51.0
+exceptiongroup==1.2.2
+fastapi==0.111.1
+fastapi-cli==0.0.4
+filelock==3.15.4
+fonttools==4.53.1
 frozenlist==1.4.1
 fsspec==2023.10.0
-gekko==1.1.1
+gekko==1.2.1
 graphviz==0.20.3
 greenlet==3.0.3
 h11==0.14.0
 hjson==3.1.0
 httpcore==1.0.5
 httptools==0.6.1
 httpx==0.27.0
-huggingface-hub==0.23.0
-humanfriendly==10.0
+huggingface-hub==0.24.1
 idna==3.7
 interegular==0.3.3
 Jinja2==3.1.4
 joblib==1.4.2
 jsonpatch==1.33
-jsonpointer==2.4
-jsonschema==4.22.0
+jsonpointer==3.0.0
+jsonschema==4.23.0
 jsonschema-specifications==2023.12.1
 kiwisolver==1.4.5
-langchain==0.1.19
-langchain-community==0.0.38
-langchain-core==0.1.52
-langchain-text-splitters==0.0.1
-langsmith==0.1.56
+langchain==0.2.11
+langchain-core==0.2.23
+langchain-text-splitters==0.2.2
+langsmith==0.1.93
 lark==1.1.9
-lightgbm==4.3.0
-llvmlite==0.42.0
-lm-format-enforcer==0.9.8
-lxml==5.2.1
+lightgbm==4.4.0
+llvmlite==0.43.0
+lm-format-enforcer==0.10.3
+lxml==5.2.2
 markdown-it-py==3.0.0
 MarkupSafe==2.1.5
-marshmallow==3.21.2
-matplotlib==3.8.4
+matplotlib==3.9.1
 mdurl==0.1.2
 mpmath==1.3.0
 msgpack==1.0.8
 multidict==6.0.5
 multiprocess==0.70.15
-mypy-extensions==1.0.0
 nest-asyncio==1.6.0
 networkx==3.3
 ninja==1.11.1.1
-numba==0.59.1
+numba==0.60.0
 numpy==1.26.4
 nvidia-cublas-cu12==12.1.3.1
 nvidia-cuda-cupti-cu12==12.1.105
@@ -89,85 +83,84 @@ nvidia-cufft-cu12==11.0.2.54
 nvidia-curand-cu12==10.3.2.106
 nvidia-cusolver-cu12==11.4.5.107
 nvidia-cusparse-cu12==12.1.0.106
-nvidia-ml-py==12.550.52
+nvidia-ml-py==12.555.43
 nvidia-nccl-cu12==2.20.5
-nvidia-nvjitlink-cu12==12.4.127
+nvidia-nvjitlink-cu12==12.5.82
 nvidia-nvtx-cu12==12.1.105
-openai==1.28.0
-optimum==1.19.2
-orjson==3.10.3
-outlines==0.0.34
-packaging==23.2
+openai==1.37.0
+orjson==3.10.6
+outlines==0.0.46
+packaging==24.1
 pandas==2.2.2
-peft==0.10.0
-pillow==10.3.0
-plotly==5.22.0
-portalocker==2.8.2
+peft==0.11.1
+pillow==10.4.0
+plotly==5.23.0
+portalocker==2.10.1
 prometheus-fastapi-instrumentator==7.0.0
 prometheus_client==0.20.0
-protobuf==5.26.1
-psutil==5.9.8
+protobuf==5.27.2
+psutil==6.0.0
 py-cpuinfo==9.0.0
+pyairports==2.1.1
 pyarrow==11.0.0
 pyarrow-hotfix==0.6
-pydantic==2.7.1
-pydantic_core==2.18.2
+pycountry==24.6.1
+pydantic==2.8.2
+pydantic_core==2.20.1
 Pygments==2.18.0
-pynvml==11.5.0
 pyparsing==3.1.2
 python-dateutil==2.9.0.post0
 python-dotenv==1.0.1
 python-multipart==0.0.9
 pytz==2024.1
 PyYAML==6.0.1
-ray==2.21.0
+pyzmq==26.0.3
+ray==2.32.0
 referencing==0.35.1
-regex==2024.5.10
-requests==2.31.0
+regex==2024.5.15
+requests==2.32.3
 rich==13.7.1
 rouge==1.0.1
-rpds-py==0.18.1
+rpds-py==0.19.0
 sacrebleu==2.4.2
 sacremoses==0.1.1
 safetensors==0.4.3
-scikit-learn==1.4.2
-scipy==1.13.0
-sentence-transformers==2.7.0
+scikit-learn==1.5.1
+scipy==1.14.0
+sentence-transformers==3.0.1
 sentencepiece==0.2.0
 shellingham==1.5.4
 shtab==1.7.1
 six==1.16.0
 sniffio==1.3.1
-SQLAlchemy==2.0.30
+SQLAlchemy==2.0.31
 starlette==0.37.2
-sympy==1.12
+sympy==1.13.1
 tabulate==0.9.0
-tenacity==8.3.0
+tenacity==8.5.0
 threadpoolctl==3.5.0
-tiktoken==0.6.0
+tiktoken==0.7.0
 tokenizers==0.19.1
-torch==2.3.0
-torchaudio==2.3.0
-torchvision==0.18.0
+torch==2.3.1
+torchaudio==2.3.1
+torchvision==0.18.1
 tqdm==4.66.4
-transformers==4.40.2
+transformers==4.43.1
 transformers-stream-generator==0.0.5
-triton==2.3.0
-trl==0.8.6
+triton==2.3.1
+trl==0.9.6
 typer==0.12.3
-typing-inspect==0.9.0
-typing_extensions==4.11.0
-tyro==0.8.4
+typing_extensions==4.12.2
+tyro==0.8.5
 tzdata==2024.1
-ujson==5.9.0
-urllib3==2.2.1
-uvicorn==0.29.0
+urllib3==2.2.2
+uvicorn==0.30.3
 uvloop==0.19.0
-vllm==0.4.2
-vllm-nccl-cu12==2.18.1.0.4.0
-watchfiles==0.21.0
+vllm==0.5.3.post1
+vllm-flash-attn==2.5.9.post1
+watchfiles==0.22.0
 websockets==12.0
-xformers==0.0.26.post1
-xgboost==2.0.3
+xformers==0.0.27
+xgboost==2.1.0
 xxhash==3.4.1
 yarl==1.9.4
diff --git a/pgml-extension/requirements.txt b/pgml-extension/requirements.txt
@@ -30,7 +30,6 @@ ctransformers
 huggingface-hub
 deepspeed
 einops
-optimum
 peft
 tokenizers
 transformers
diff --git a/pgml-extension/sql/pgml--2.9.2--2.9.3.sql b/pgml-extension/sql/pgml--2.9.2--2.9.3.sql

Original file line number	Diff line number	Diff line change
`@@ -4,7 +4,7 @@ on:`
`4`	`4`	`workflow_dispatch:`
`5`	`5`	`inputs:`
`6`	`6`	`packageVersion:`
`7`		`- default: "2.9.2"`
	`7`	`+ default: "2.9.3"`
`8`	`8`	`jobs:`
`9`	`9`	`#`
`10`	`10`	`# PostgresML extension.`
-Original file line number
+Diff line change
 pgml_test=# SELECT pgml.version();
  version
 ---------
 - 2.9.2
 + 2.9.3
 (1 row)
 ```