strip only starting 'v' char; e.g don't strip from '.dev'

* upgrade transformers to 4.57.5

* explicitly set versions for fbgemm-gpu

* handle index url for cuda version

* explicitly set cu version for fbgemm deps, skip for 130

* cu suffix not needed on version if using whl subpath

.github/workflows/multi-gpu-e2e.yml

@@ -47,7 +47,8 @@ jobs:
             cuda_version: 13.0.0
             python_version: "3.11"
             pytorch: 2.9.1
-            axolotl_extras: fbgemm-gpu
+            axolotl_extras:
+#            axolotl_extras: fbgemm-gpu
             num_gpus: 2
             nightly_build: "true"
     runs-on: [self-hosted, modal]

.github/workflows/pypi.yml

@@ -48,9 +48,9 @@ jobs:
         id: tag
         run: echo ::set-output name=TAG_NAME::$(echo $GITHUB_REF | cut -d / -f 3)
 
-      - name: Update version in setup.py
+      - name: Update version in VERSION file
         run: |
-          sed -i -E 's/version="([0-9.]+)",/version="${{ steps.tag.outputs.TAG_NAME }}",/g' setup.py
+          echo "${{ steps.tag.outputs.TAG_NAME }}" | sed 's/^v//' > VERSION
 
       - name: Build a source dist
         run: |

VERSION

@@ -0,0 +1 @@
+0.14.0.dev0

pyproject.toml

@@ -24,6 +24,9 @@ Repository = "https://github.com/axolotl-ai-cloud/axolotl.git"
 py-modules = ["setuptools_axolotl_dynamic_dependencies"]
 include-package-data = true
 
+[tool.setuptools.dynamic]
+version = { file = "VERSION" }
+
 [tool.setuptools.cmdclass]
 build_py = "setuptools_axolotl_dynamic_dependencies.BuildPyCommand"
 

requirements.txt

@@ -11,11 +11,11 @@ liger-kernel==0.6.4
 packaging==23.2
 
 huggingface_hub>=0.36.0
-peft>=0.18.0
+peft>=0.18.1
 tokenizers>=0.22.1
-transformers==4.57.1
+transformers==4.57.6
 accelerate==1.12.0
-datasets==4.4.2
+datasets==4.5.0
 deepspeed>=0.18.3
 trl==0.25.1
 hf_xet==1.2.0

setup.py

@@ -1,6 +1,5 @@
 """setup.py for axolotl"""
 
-import ast
 import os
 import platform
 import re
@@ -26,6 +25,7 @@ def parse_requirements(extras_require_map):
                 _install_requires.append(line)
     try:
         xformers_version = [req for req in _install_requires if "xformers" in req][0]
+        install_xformers = platform.machine() != "aarch64"
         if "Darwin" in platform.system():
             # skip packages not compatible with OSX
             skip_packages = [
@@ -62,44 +62,63 @@ def parse_requirements(extras_require_map):
             else:
                 raise ValueError("Invalid version format")
 
+            torch_parts = torch_version.split("+")
+            if len(torch_parts) == 2:
+                torch_cuda_version = torch_parts[1]
+                _dependency_links.append(
+                    f"https://download.pytorch.org/whl/{torch_cuda_version}"
+                )
+
             if (major, minor) >= (2, 9):
                 extras_require_map.pop("fbgemm-gpu")
-                extras_require_map["fbgemm-gpu"] = ["fbgemm-gpu-genai==1.4.1"]
+                extras_require_map["fbgemm-gpu"] = [
+                    "fbgemm-gpu==1.4.0",
+                    "fbgemm-gpu-genai==1.4.2",
+                ]
                 extras_require_map["vllm"] = ["vllm==0.11.1"]
+                if not install_xformers:
+                    _install_requires.pop(_install_requires.index(xformers_version))
             elif (major, minor) >= (2, 8):
                 extras_require_map.pop("fbgemm-gpu")
                 extras_require_map["fbgemm-gpu"] = ["fbgemm-gpu-genai==1.3.0"]
                 extras_require_map["vllm"] = ["vllm==0.11.0"]
+                if not install_xformers:
+                    _install_requires.pop(_install_requires.index(xformers_version))
             elif (major, minor) >= (2, 7):
                 _install_requires.pop(_install_requires.index(xformers_version))
                 if patch == 0:
-                    _install_requires.append("xformers==0.0.30")
+                    if install_xformers:
+                        _install_requires.append("xformers==0.0.30")
                     # vllm 0.9.x is incompatible with latest transformers
                     extras_require_map.pop("vllm")
                 else:
-                    _install_requires.append("xformers==0.0.31")
+                    if install_xformers:
+                        _install_requires.append("xformers==0.0.31")
                     extras_require_map["vllm"] = ["vllm==0.10.1"]
             elif (major, minor) >= (2, 6):
                 _install_requires.pop(_install_requires.index(xformers_version))
-                _install_requires.append("xformers==0.0.29.post3")
+                if install_xformers:
+                    _install_requires.append("xformers==0.0.29.post3")
                 # since we only support 2.6.0+cu126
                 _dependency_links.append("https://download.pytorch.org/whl/cu126")
                 extras_require_map.pop("vllm")
             elif (major, minor) >= (2, 5):
                 _install_requires.pop(_install_requires.index(xformers_version))
-                if patch == 0:
+                if install_xformers:
-                    _install_requires.append("xformers==0.0.28.post2")
+                    if patch == 0:
-                else:
+                        _install_requires.append("xformers==0.0.28.post2")
-                    _install_requires.append("xformers>=0.0.28.post3")
+                    else:
+                        _install_requires.append("xformers>=0.0.28.post3")
                 extras_require_map.pop("vllm")
             elif (major, minor) >= (2, 4):
                 extras_require_map.pop("vllm")
-                if patch == 0:
+                if install_xformers:
-                    _install_requires.pop(_install_requires.index(xformers_version))
+                    if patch == 0:
-                    _install_requires.append("xformers>=0.0.27")
+                        _install_requires.pop(_install_requires.index(xformers_version))
-                else:
+                        _install_requires.append("xformers>=0.0.27")
-                    _install_requires.pop(_install_requires.index(xformers_version))
+                    else:
-                    _install_requires.append("xformers==0.0.28.post1")
+                        _install_requires.pop(_install_requires.index(xformers_version))
+                        _install_requires.append("xformers==0.0.28.post1")
             else:
                 raise ValueError("axolotl requires torch>=2.4")
 
@@ -110,15 +129,11 @@ def parse_requirements(extras_require_map):
 
 def get_package_version():
     with open(
-        Path(os.path.dirname(os.path.abspath(__file__)))
+        Path(os.path.dirname(os.path.abspath(__file__))) / "VERSION",
-        / "src"
-        / "axolotl"
-        / "__init__.py",
         "r",
         encoding="utf-8",
     ) as fin:
-        version_match = re.search(r"^__version__\s*=\s*(.*)$", fin.read(), re.MULTILINE)
+        version_ = fin.read().strip()
-    version_ = ast.literal_eval(version_match.group(1))
     return version_
 
 

src/axolotl/__init__.py

@@ -1,7 +1,11 @@
 """Axolotl - Train and fine-tune large language models"""
 
 import pkgutil
+from importlib.metadata import PackageNotFoundError, version
 
 __path__ = pkgutil.extend_path(__path__, __name__)  # Make this a namespace package
 
-__version__ = "0.13.0.dev"
+try:
+    __version__ = version("axolotl")
+except PackageNotFoundError:
+    __version__ = "unknown"