Skip to content

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.

Add cu128/cu126/cu130 torch 2.11.0 extras (torch2110) with xformers 0.0.35 (#6955)

Daniel Hancc33ff215166
diff --git a/pyproject.toml b/pyproject.toml
index 3e1dcf2c611..39369ba73e9 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -458,16 +458,73 @@ cu130onlytorch291 = [
"xformers @ https://download.pytorch.org/whl/cu130/xformers-0.0.33.post2-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32')",
]
cu126onlytorch2100 = [
- "xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.34-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform)",
- "xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.34-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32')",
+ # Pin torch so ARM64 (x86-64-only xformers wheel skipped) stays on 2.10.
+ "torch==2.10.0",
+ "xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.34-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform) and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
+ "xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.34-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
]
cu128onlytorch2100 = [
- "xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.34-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform)",
- "xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.34-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32')",
+ "torch==2.10.0",
+ "xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.34-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform) and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
+ "xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.34-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
]
cu130onlytorch2100 = [
- "xformers @ https://download.pytorch.org/whl/cu130/xformers-0.0.34-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform)",
- "xformers @ https://download.pytorch.org/whl/cu130/xformers-0.0.34-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32')",
+ "torch==2.10.0",
+ "xformers @ https://download.pytorch.org/whl/cu130/xformers-0.0.34-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform) and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
+ "xformers @ https://download.pytorch.org/whl/cu130/xformers-0.0.34-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
+]
+cu126onlytorch2110 = [
+ # Pin the trio to +cuNNN: torch 2.11+ defaults to a CUDA-13 wheel and xformers 0.0.35
+ # does not pin torch. == not a range (+cu126 wins, PEP 440) and not === (force-replaces).
+ "torch==2.11.0+cu126",
+ "torchvision==0.26.0+cu126",
+ "torchaudio==2.11.0+cu126",
+ "xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.35-py39-none-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform) and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
+ "xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.35-py39-none-win_amd64.whl ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
+]
+cu128onlytorch2110 = [
+ "torch==2.11.0+cu128",
+ "torchvision==0.26.0+cu128",
+ "torchaudio==2.11.0+cu128",
+ "xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.35-py39-none-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform) and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
+ "xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.35-py39-none-win_amd64.whl ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
+]
+cu130onlytorch2110 = [
+ "torch==2.11.0+cu130",
+ "torchvision==0.26.0+cu130",
+ "torchaudio==2.11.0+cu130",
+ "xformers @ https://download.pytorch.org/whl/cu130/xformers-0.0.35-py39-none-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform) and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
+ "xformers @ https://download.pytorch.org/whl/cu130/xformers-0.0.35-py39-none-win_amd64.whl ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
+]
+# torch 2.12 ships on cu126/cu130 only, so no cu128 leaf; torchaudio has no 2.12 release.
+cu126onlytorch2120 = [
+ "torch==2.12.0+cu126",
+ "torchvision==0.27.0+cu126",
+ "torchaudio==2.11.0+cu126",
+ "xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.35-py39-none-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform) and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
+ "xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.35-py39-none-win_amd64.whl ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
+]
+cu130onlytorch2120 = [
+ "torch==2.12.0+cu130",
+ "torchvision==0.27.0+cu130",
+ "torchaudio==2.11.0+cu130",
+ "xformers @ https://download.pytorch.org/whl/cu130/xformers-0.0.35-py39-none-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform) and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
+ "xformers @ https://download.pytorch.org/whl/cu130/xformers-0.0.35-py39-none-win_amd64.whl ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
+]
+cu126onlytorch2121 = [
+ # torchvision exact-pins torch, so the 2.12.1 patch takes 0.27.1.
+ "torch==2.12.1+cu126",
+ "torchvision==0.27.1+cu126",
+ "torchaudio==2.11.0+cu126",
+ "xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.35-py39-none-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform) and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
+ "xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.35-py39-none-win_amd64.whl ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
+]
+cu130onlytorch2121 = [
+ "torch==2.12.1+cu130",
+ "torchvision==0.27.1+cu130",
+ "torchaudio==2.11.0+cu130",
+ "xformers @ https://download.pytorch.org/whl/cu130/xformers-0.0.35-py39-none-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform) and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
+ "xformers @ https://download.pytorch.org/whl/cu130/xformers-0.0.35-py39-none-win_amd64.whl ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
]
cu118 = [
"unsloth[huggingface]",
@@ -677,6 +734,41 @@ cu130-torch2100 = [
"unsloth[cu130onlytorch2100]",
"unsloth[audio-torch210]",
]
+cu126-torch2110 = [
+ "unsloth[huggingface]",
+ "bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
+ "unsloth[cu126onlytorch2110]",
+]
+cu128-torch2110 = [
+ "unsloth[huggingface]",
+ "bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
+ "unsloth[cu128onlytorch2110]",
+]
+cu130-torch2110 = [
+ "unsloth[huggingface]",
+ "bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
+ "unsloth[cu130onlytorch2110]",
+]
+cu126-torch2120 = [
+ "unsloth[huggingface]",
+ "bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
+ "unsloth[cu126onlytorch2120]",
+]
+cu130-torch2120 = [
+ "unsloth[huggingface]",
+ "bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
+ "unsloth[cu130onlytorch2120]",
+]
+cu126-torch2121 = [
+ "unsloth[huggingface]",
+ "bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
+ "unsloth[cu126onlytorch2121]",
+]
+cu130-torch2121 = [
+ "unsloth[huggingface]",
+ "bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
+ "unsloth[cu130onlytorch2121]",
+]
kaggle = [
"unsloth[huggingface]",
]
@@ -979,6 +1071,41 @@ cu130-ampere-torch2100 = [
"unsloth[cu130onlytorch2100]",
"unsloth[audio-torch210]",
]
+cu126-ampere-torch2110 = [
+ "unsloth[huggingface]",
+ "bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
+ "unsloth[cu126onlytorch2110]",
+]
+cu128-ampere-torch2110 = [
+ "unsloth[huggingface]",
+ "bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
+ "unsloth[cu128onlytorch2110]",
+]
+cu130-ampere-torch2110 = [
+ "unsloth[huggingface]",
+ "bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
+ "unsloth[cu130onlytorch2110]",
+]
+cu126-ampere-torch2120 = [
+ "unsloth[huggingface]",
+ "bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
+ "unsloth[cu126onlytorch2120]",
+]
+cu130-ampere-torch2120 = [
+ "unsloth[huggingface]",
+ "bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
+ "unsloth[cu130onlytorch2120]",
+]
+cu126-ampere-torch2121 = [
+ "unsloth[huggingface]",
+ "bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
+ "unsloth[cu126onlytorch2121]",
+]
+cu130-ampere-torch2121 = [
+ "unsloth[huggingface]",
+ "bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
+ "unsloth[cu130onlytorch2121]",
+]
flashattentiontorch260abiFALSEcu12x = [
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp39-cp39-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.9'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp310-cp310-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.10'",
diff --git a/tests/python/test_windows_xformers_wheel_match.py b/tests/python/test_windows_xformers_wheel_match.py
index 4865bafcc9f..3cfbd99abfd 100644
--- a/tests/python/test_windows_xformers_wheel_match.py
+++ b/tests/python/test_windows_xformers_wheel_match.py
@@ -51,12 +51,9 @@ XFORMERS_WHEEL_MATRIX: dict[tuple[str, str], str] = {
("cu130", "2100"): "0.0.34",
}
-# torch 2.11 publishes no xFormers wheel on any index yet, and the Windows torch
-# pin in install.ps1 is torch<2.11.0 for exactly that kind of reason. Assert the
-# absence so a future 2.11 row has to be added deliberately (with a live wheel)
-# rather than inherited from 2.10 -- xFormers' extension ABI does not survive a
-# torch minor bump, so reusing the 2.10 wheel there would reintroduce this bug.
-TORCH_RELEASES_WITHOUT_XFORMERS_WHEELS = ("2110",)
+# Torch releases with no xFormers wheel on any index; naming one in an extra would resolve
+# a wheel built for a different torch. Empty: 0.0.35 is stable-ABI and loads under 2.11 up.
+TORCH_RELEASES_WITHOUT_XFORMERS_WHEELS: tuple[str, ...] = ()
def _tomllib():
diff --git a/tests/test_torch2110_cuda_extras.py b/tests/test_torch2110_cuda_extras.py
new file mode 100644
index 00000000000..c467d653824
--- /dev/null
+++ b/tests/test_torch2110_cuda_extras.py
@@ -0,0 +1,172 @@
+# Unsloth Zoo - Utilities for Unsloth
+# Copyright 2023-present Daniel Han-Chen, Michael Han-Chen & the Unsloth team. All rights reserved.
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published
+# by the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program. If not, see <https://www.gnu.org/licenses/>.
+
+"""Regression guard: the CUDA torch2110 / torch212x extras must pin the torch trio to the
+matching +cuXXX local build (xformers 0.0.35 does not pin torch), else resolution walks
+torch up to a release the xformers wheel was not built for. Parses files only, no network.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+import pytest
+from packaging.requirements import Requirement
+
+try:
+ import tomllib
+except ModuleNotFoundError: # pragma: no cover
+ tomllib = pytest.importorskip("tomli")
+
+REPO = Path(__file__).resolve().parents[1]
+PYPROJECT = REPO / "pyproject.toml"
+AUTO_INSTALL = REPO / "unsloth" / "_auto_install.py"
+_TORCH_TRIO = ("torch", "torchvision", "torchaudio")
+# torchaudio has no 2.12 release, so the 2.12 leaves keep 2.11.0.
+_TORCH212_TRIO = {
+ "torch2120": {"torch": "2.12.0", "torchvision": "0.27.0", "torchaudio": "2.11.0"},
+ "torch2121": {"torch": "2.12.1", "torchvision": "0.27.1", "torchaudio": "2.11.0"},
+}
+_TORCH212_CUDA = ("cu126", "cu130")
+
+
+def _extras() -> dict[str, list[str]]:
+ with open(PYPROJECT, "rb") as f:
+ data = tomllib.load(f)
+ return data["project"]["optional-dependencies"]
+
+
+def _extra(name: str) -> list[str]:
+ return _extras()[name]
+
+
+def _reqs(specs: list[str]) -> dict[str, list[Requirement]]:
+ out: dict[str, list[Requirement]] = {}
+ for spec in specs:
+ r = Requirement(spec)
+ out.setdefault(r.name.lower(), []).append(r)
+ return out
+
+
[email protected]("cuda", ["cu126", "cu128", "cu130"])
+def test_cuda12_torch2110_pins_matching_local_build(cuda: str):
+ reqs = _reqs(_extra(f"{cuda}onlytorch2110"))
+ for pkg in _TORCH_TRIO:
+ (req,) = reqs[pkg]
+ spec = str(req.specifier)
+ assert (
+ spec == f"=={('2.11.0' if pkg != 'torchvision' else '0.26.0')}+{cuda}"
+ ), f"{cuda}onlytorch2110: {pkg} pinned as '{spec}', expected the +{cuda} local build"
+ xformers = reqs["xformers"]
+ assert len(xformers) == 2, f"expected Linux + Windows xformers wheels, got {xformers}"
+ linux = [r for r in xformers if r.url and r.url.endswith("manylinux_2_28_x86_64.whl")]
+ windows = [r for r in xformers if r.url and r.url.endswith("win_amd64.whl")]
+ assert len(linux) == 1 and len(windows) == 1, f"unexpected xformers wheels: {xformers}"
+ for r in linux + windows:
+ assert (
+ f"/whl/{cuda}/xformers-0.0.35-" in r.url
+ ), f"xformers not on the {cuda} index: {r.url}"
+ assert r.marker is not None
+ assert not r.marker.evaluate({"sys_platform": "linux", "platform_machine": "aarch64"})
+ assert not r.marker.evaluate({"sys_platform": "win32", "platform_machine": "ARM64"})
+ assert linux[0].marker.evaluate({"sys_platform": "linux", "platform_machine": "x86_64"})
+ assert windows[0].marker.evaluate({"sys_platform": "win32", "platform_machine": "AMD64"})
+
+
[email protected]("cuda", ["cu126", "cu128", "cu130"])
[email protected]("variant", ["", "ampere-"])
+def test_torch2110_wrapper_references_matching_leaf(cuda: str, variant: str):
+ specs = _extra(f"{cuda}-{variant}torch2110")
+ assert specs == [
+ "unsloth[huggingface]",
+ "bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
+ f"unsloth[{cuda}onlytorch2110]",
+ ]
+
+
[email protected]("cuda", _TORCH212_CUDA)
[email protected]("series", sorted(_TORCH212_TRIO))
+def test_cuda12_torch212_pins_matching_local_build(cuda: str, series: str):
+ reqs = _reqs(_extra(f"{cuda}only{series}"))
+ for pkg, want in _TORCH212_TRIO[series].items():
+ (req,) = reqs[pkg]
+ spec = str(req.specifier)
+ assert spec == f"=={want}+{cuda}", (
+ f"{cuda}only{series}: {pkg} pinned as '{spec}', "
+ f"expected the =={want}+{cuda} local build"
+ )
+ assert req.marker is None, f"the {pkg} pin must apply on every machine"
+ xformers = reqs["xformers"]
+ linux = [r for r in xformers if r.url and r.url.endswith("manylinux_2_28_x86_64.whl")]
+ windows = [r for r in xformers if r.url and r.url.endswith("win_amd64.whl")]
+ assert len(linux) == 1 and len(windows) == 1, f"unexpected xformers wheels: {xformers}"
+ for r in linux + windows:
+ assert (
+ f"/whl/{cuda}/xformers-0.0.35-" in r.url
+ ), f"xformers not on the {cuda} index: {r.url}"
+ assert r.marker is not None
+ assert not r.marker.evaluate({"sys_platform": "linux", "platform_machine": "aarch64"})
+ assert not r.marker.evaluate({"sys_platform": "win32", "platform_machine": "ARM64"})
+ assert linux[0].marker.evaluate({"sys_platform": "linux", "platform_machine": "x86_64"})
+ assert windows[0].marker.evaluate({"sys_platform": "win32", "platform_machine": "AMD64"})
+
+
[email protected]("cuda", _TORCH212_CUDA)
[email protected]("series", sorted(_TORCH212_TRIO))
[email protected]("variant", ["", "ampere-"])
+def test_torch212_wrapper_references_matching_leaf(cuda: str, series: str, variant: str):
+ specs = _extra(f"{cuda}-{variant}{series}")
+ assert specs == [
+ "unsloth[huggingface]",
+ "bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
+ f"unsloth[{cuda}only{series}]",
+ ]
+
+
[email protected]("series", sorted(_TORCH212_TRIO))
+def test_no_cu128_torch212_extras(series: str):
+ names = _extras()
+ for name in (f"cu128only{series}", f"cu128-{series}", f"cu128-ampere-{series}"):
+ assert name not in names, f"{name} cannot resolve: no torch 2.12 on the cu128 index"
+
+
[email protected]("series", sorted(_TORCH212_TRIO))
+def test_auto_install_maps_torch212_to_defined_extras(series: str):
+ # The printed command must name existing extras and add the index serving their pins.
+ source = AUTO_INSTALL.read_text(encoding = "utf-8")
+ assert f"'cu{{}}{{}}-{series}'" in source, f"_auto_install.py never selects {series}"
+ assert f"'-{series}'" in source, f"{series} missing from the extra-index-url gate"
+ names = _extras()
+ for cuda in _TORCH212_CUDA:
+ for variant in ("", "-ampere"):
+ assert f"cu{cuda[2:]}{variant}-{series}" in names
+
+
+def test_auto_install_rejects_cuda128_on_torch212():
+ # cu128 tops out at torch 2.11, so 2.12 there must fail rather than name a missing extra.
+ source = AUTO_INSTALL.read_text(encoding = "utf-8")
+ assert 'if v >= V(\'2.12.0\') and cuda not in ("12.6", "13.0")' in source
+
+
[email protected]("cuda", ["cu126", "cu128", "cu130"])
+def test_cuda12_torch2100_keeps_torch_pinned_off_x86(cuda: str):
+ reqs = _reqs(_extra(f"{cuda}onlytorch2100"))
+ (torch_req,) = reqs["torch"]
+ assert str(torch_req.specifier) == "==2.10.0", (
+ f"{cuda}onlytorch2100 must pin torch==2.10.0 for machines where the "
+ f"x86-64-only xformers wheel (and its transitive pin) is skipped"
+ )
+ assert torch_req.marker is None, "the torch pin must apply on every machine"
diff --git a/unsloth/_auto_install.py b/unsloth/_auto_install.py
index d34e09e89c2..c0c4d432606 100644
--- a/unsloth/_auto_install.py
+++ b/unsloth/_auto_install.py
@@ -36,8 +36,17 @@ elif v < V('2.8.9'): x = 'cu{}{}-torch280'
elif v < V('2.9.1'): x = 'cu{}{}-torch290'
elif v < V('2.9.2'): x = 'cu{}{}-torch291'
elif v < V('2.10.1'): x = 'cu{}{}-torch2100'
+elif v < V('2.11.0'): raise RuntimeError(f"Torch = {v} not supported!")
+elif v < V('2.11.1'): x = 'cu{}{}-torch2110'
+elif v < V('2.12.0'): raise RuntimeError(f"Torch = {v} not supported!")
+elif v < V('2.12.1'): x = 'cu{}{}-torch2120'
+elif v < V('2.12.2'): x = 'cu{}{}-torch2121'
else: raise RuntimeError(f"Torch = {v} too new!")
if v > V('2.6.9') and cuda not in ("11.8", "12.6", "12.8", "13.0"): raise RuntimeError(f"CUDA = {cuda} not supported!")
-if v >= V('2.10.0') and cuda not in ("12.6", "12.8", "13.0"): raise RuntimeError(f"Torch 2.10 requires CUDA 12.6, 12.8, or 13.0! Got CUDA = {cuda}")
+if v >= V('2.10.0') and cuda not in ("12.6", "12.8", "13.0"): raise RuntimeError(f"Torch = {v} requires CUDA 12.6, 12.8, or 13.0! Got CUDA = {cuda}")
+# torch 2.12 ships on cu126/cu130 only, and cu126 builds stop at sm_90, so Blackwell needs CUDA 13.
+if v >= V('2.12.0') and cuda not in ("12.6", "13.0"): raise RuntimeError(f"Torch = {v} requires CUDA 12.6 or 13.0! Got CUDA = {cuda}")
x = x.format(cuda.replace(".", ""), "-ampere" if False else "") # is_ampere is broken due to flash-attn
-print(f'pip install --upgrade pip setuptools wheel && pip install --no-deps git+https://github.com/unslothai/unsloth-zoo.git && pip install "unsloth[{x}] @ git+https://github.com/unslothai/unsloth.git" --no-build-isolation')
\ No newline at end of file
+# torch2110+ extras pin +cuNNN builds, which resolve only from the matching index.
+extra_index = f' --extra-index-url https://download.pytorch.org/whl/cu{cuda.replace(".", "")}' if (x.endswith(('-torch2110', '-torch2120', '-torch2121')) and cuda in ("12.6", "12.8", "13.0")) else ''
+print(f'pip install --upgrade pip setuptools wheel && pip install --no-deps git+https://github.com/unslothai/unsloth-zoo.git && pip install "unsloth[{x}] @ git+https://github.com/unslothai/unsloth.git" --no-build-isolation{extra_index}')
\ No newline at end of file