Docs: Preparing 0.9.0

noamgat · Feb 19, 2024 · 6372420 · 6372420
1 parent 501e256
commit 6372420
Show file tree

Hide file tree

Showing 6 changed files with 25 additions and 16 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,10 @@
 # LM Format Enforcer Changelog
 
+## v0.9.0
+- [#68](https://github.com/noamgat/lm-format-enforcer/pull/68) Added NVIDIA TensorRT-LLM Support, [Ahmet Erdem](https://github.com/aerdem4)'s contribution.
+- Much faster TokenizerData initialization, new JSON freetext token caching algorithm.
+- More robust error reporting.
+
 ## v0.8.3
 - [#67](https://github.com/noamgat/lm-format-enforcer/issues/67) Updating vLLM integration to support v0.3.0
 - [#63](https://github.com/noamgat/lm-format-enforcer/issues/63) JSONSchemaParser: Empty list cannot be closed after a newline

diff --git a/CONTRIBUTORS.md b/CONTRIBUTORS.md
@@ -5,6 +5,7 @@
 * [Noam Gat](https://github.com/noamgat) (Main Author)
 * [Jarno Elonen](https://github.com/elonen) (Improved performance of length-limited json strings)
 * [Benedikt Fuchs](https://github.com/helpmefindaname) (Bug fixes)
+* [Ahmet Erdem](https://github.com/aerdem4) (NVIDIA TensorRT-LLM support)
 
 ## I would like to join this list. How can I help the project?
 

diff --git a/README.md b/README.md
@@ -58,7 +58,7 @@ print(result)
 
 ## Capabilities / Advantages
 
-- Works with any Python language model and tokenizer. Already supports [transformers](https://github.com/huggingface/transformers), [LangChain](https://python.langchain.com/docs/integrations/llms/lmformatenforcer_experimental), [LlamaIndex](https://docs.llamaindex.ai/en/latest/community/integrations/lmformatenforcer.html), [llama.cpp](https://github.com/noamgat/lm-format-enforcer/blob/main/samples/colab_llamacpppython_integration.ipynb), [vLLM](https://github.com/noamgat/lm-format-enforcer/blob/main/samples/colab_vllm_integration.ipynb), [Haystack](https://haystack.deepset.ai/integrations/lmformatenforcer) and [ExLlamaV2](https://github.com/noamgat/lm-format-enforcer/blob/main/samples/colab_exllamav2_integration.ipynb). Can be adapted to others.
+- Works with any Python language model and tokenizer. Already supports [transformers](https://github.com/huggingface/transformers), [LangChain](https://python.langchain.com/docs/integrations/llms/lmformatenforcer_experimental), [LlamaIndex](https://docs.llamaindex.ai/en/latest/community/integrations/lmformatenforcer.html), [llama.cpp](https://github.com/noamgat/lm-format-enforcer/blob/main/samples/colab_llamacpppython_integration.ipynb), [vLLM](https://github.com/noamgat/lm-format-enforcer/blob/main/samples/colab_vllm_integration.ipynb), [Haystack](https://haystack.deepset.ai/integrations/lmformatenforcer), [NVIDIA TensorRT-LLM](https://github.com/noamgat/lm-format-enforcer/blob/main/samples/colab_trtllm_integration.ipynb) and [ExLlamaV2](https://github.com/noamgat/lm-format-enforcer/blob/main/samples/colab_exllamav2_integration.ipynb).
 - Supports batched generation and beam searches - each input / beam can have different tokens filtered at every timestep
 - Supports JSON Schema, JSON Mode (schemaless) and Regular Expression formats
 - Supports both required and optional fields in JSON schemas

diff --git a/docs/Intro.drawio b/docs/Intro.drawio
diff --git a/docs/Intro.webp b/docs/Intro.webp
diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "lm-format-enforcer"
-version = "0.8.3"
+version = "0.9.0"
 description = "Enforce the output format (JSON Schema, Regex etc) of a language model"
 authors = ["Noam Gat <[email protected]>"]
 license = "MIT"