Dependencies: Switch to LM-format-enforcer fork

LM format enforcer has some latency on token ingestion, so use an
optimized fork instead. Also add this in as a base dependency since
the size is small.

Signed-off-by: kingbri <bdashore3@proton.me>

backends/exllamav2/grammar.py

@@ -72,8 +72,8 @@ class ExLlamaV2Grammar:
                 "Skipping JSON schema parsing because "
                 "lm-format-enforcer is not installed.\n"
                 "Please run the following command in your environment "
-                "to install extra packages:\n"
-                "pip install -U .[extras]"
+                "to reinstall dependencies:\n"
+                "pip install -U ."
             )
 
             return

pyproject.toml

@@ -26,6 +26,7 @@ dependencies = [
     "sse-starlette",
     "packaging",
     "tokenizers",
+    "lm-format-enforcer @ git+https://github.com/theroyallab/lm-format-enforcer",
 ]
 
 [project.urls]
@@ -33,8 +34,8 @@ dependencies = [
 
 [project.optional-dependencies]
 extras = [
-    "outlines",
-    "lm-format-enforcer",
+    # Heavy dependencies that aren't for everyday use
+    "outlines"
 ]
 dev = [
     "ruff == 0.3.2"