Bug fixes (#3322)
* Fix mamba * Update loader.py * Update vision.py * Update loader.py * Filter vLLM standby logs (#3131) * filter vLLM standby logs * safeguard standby logger patch * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update loader.py * Add scaler * Update llama.py * Update _utils.py * Versioning * GPT OSS fix * GPT OSS fix * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Versioning * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Upcast norms * Update loader.py * Update vision.py * Upcast layernorms * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update save.py * Update rl.py * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py * Update loader.py * UNSLOTH_ENABLE_CCE * Fix * Update loader.py * Update loader.py * Update __init__.py * Update __init__.py * Update __init__.py * Update __init__.py * Import fixes * Update loader.py * Fix aimv2 issue * Update loader.py * Update import_fixes.py * Update import_fixes.py * Update loader.py * Update loader.py * Update loader.py * Upgrade * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * custom_datatype * recheck * Float16 * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Bug fix * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * torch_dtype * Update rl.py * Fix CE Loss * Versioning * Update loader.py * Update loader.py * extract_model_type_from_config * Model types * Update loader.py * get_transformers_model_type * Update loader.py * Update loader.py * Update loader.py * Update rl.py * Update pyproject.toml * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Versioning * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com>
This commit is contained in:
Daniel Han
GitHub
parent
e204e93599
commit
4af624557f
4 changed files with 25 additions and 9 deletions
|
|
@ -37,7 +37,7 @@ triton = [
|
|||
]
|
||||
|
||||
huggingface = [
|
||||
"unsloth_zoo>=2025.9.5",
|
||||
"unsloth_zoo>=2025.9.6",
|
||||
"packaging",
|
||||
"tyro",
|
||||
"transformers>=4.51.3,!=4.52.0,!=4.52.1,!=4.52.2,!=4.52.3,!=4.53.0,!=4.54.0,!=4.55.0,!=4.55.1",
|
||||
|
|
@ -453,7 +453,7 @@ colab-ampere-torch220 = [
|
|||
"flash-attn>=2.6.3",
|
||||
]
|
||||
colab-new = [
|
||||
"unsloth_zoo>=2025.9.5",
|
||||
"unsloth_zoo>=2025.9.6",
|
||||
"packaging",
|
||||
"tyro",
|
||||
"transformers>=4.51.3,!=4.47.0,!=4.52.0,!=4.52.1,!=4.52.2,!=4.52.3,!=4.53.0,!=4.54.0,!=4.55.0,!=4.55.1",
|
||||
|
|
|
|||
|
|
@ -240,7 +240,7 @@ elif DEVICE_TYPE == "xpu":
|
|||
# Check for unsloth_zoo
|
||||
try:
|
||||
unsloth_zoo_version = importlib_version("unsloth_zoo")
|
||||
if Version(unsloth_zoo_version) < Version("2025.9.5"):
|
||||
if Version(unsloth_zoo_version) < Version("2025.9.6"):
|
||||
print(
|
||||
"Unsloth: Please update Unsloth and Unsloth-Zoo to the latest version!\n"\
|
||||
"Do this via `pip install --upgrade --force-reinstall --no-cache-dir --no-deps unsloth unsloth_zoo`"
|
||||
|
|
|
|||
|
|
@ -12,7 +12,7 @@
|
|||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
__version__ = "2025.9.4"
|
||||
__version__ = "2025.9.5"
|
||||
|
||||
__all__ = [
|
||||
"SUPPORTS_BFLOAT16",
|
||||
|
|
@ -84,7 +84,7 @@ import warnings, subprocess, re, inspect, psutil, os, math
|
|||
from unsloth_zoo.utils import Version
|
||||
from importlib.metadata import version as importlib_version
|
||||
from unsloth import DEVICE_TYPE, DEVICE_COUNT
|
||||
|
||||
from unsloth_zoo.log import logger
|
||||
from unsloth_zoo.tokenizer_utils import (
|
||||
patch_tokenizer as _patch_tokenizer,
|
||||
)
|
||||
|
|
@ -608,12 +608,25 @@ elif DEVICE_TYPE == "hip":
|
|||
elif DEVICE_TYPE == "xpu":
|
||||
SUPPORTS_BFLOAT16 = True
|
||||
|
||||
from transformers.models.llama.modeling_llama import logger
|
||||
|
||||
# =============================================
|
||||
# Get Xformers
|
||||
try:
|
||||
from xformers import __version__ as xformers_version
|
||||
# [TODO] Xformers does NOT work on RTX 50x (12), B200 (10), Jetson (11)
|
||||
# See https://github.com/facebookresearch/xformers/issues/1329
|
||||
# CUDA error (/workspace/xfrm2/third_party/flash-attention/hopper/flash_fwd_launch_template.h:188)
|
||||
major_version, minor_version = torch.cuda.get_device_capability()
|
||||
if (
|
||||
(f"{major_version}.{minor_version}" in ("10.0", "11.0", "12.0")) and \
|
||||
(Version(xformers_version) in (Version("0.0.32.post2"),))
|
||||
):
|
||||
raise NotImplementedError(
|
||||
"Unsloth: Xformers does not work in RTX 50X, Blackwell GPUs as of yet. Please build from source via\n"\
|
||||
"```\n"\
|
||||
"pip install ninja\n"\
|
||||
"pip install -v --no-build-isolation -U git+https://github.com/facebookresearch/xformers.git@main#egg=xformers\n"\
|
||||
"```\n"
|
||||
)
|
||||
# Temporarily disable 0.0.27 and higher - inference issues
|
||||
if False: #Version(xformers_version) >= Version("0.0.27"):
|
||||
raise ImportError(
|
||||
|
|
@ -661,7 +674,9 @@ try:
|
|||
pass
|
||||
import xformers.ops.fmha as xformers
|
||||
xformers_attention = xformers.memory_efficient_attention
|
||||
except:
|
||||
except Exception as e:
|
||||
print("========\nSwitching to SDPA PyTorch native attention which is slightly slower.\n========\n")
|
||||
print(str(e))
|
||||
xformers = None
|
||||
xformers_attention = None
|
||||
xformers_version = None
|
||||
|
|
|
|||
|
|
@ -622,7 +622,8 @@ class FastModel(FastBaseModel):
|
|||
|
||||
# Check versions
|
||||
lowered_model_name = model_name.lower()
|
||||
os.environ["UNSLOTH_MODEL_NAME"] = lowered_model_name
|
||||
if os.environ.get("UNSLOTH_MODEL_NAME", "") == "":
|
||||
os.environ["UNSLOTH_MODEL_NAME"] = lowered_model_name
|
||||
LATEST = '\nPlease use transformers via `pip install --no-deps git+https://github.com/huggingface/transformers.git`'
|
||||
NIGHTLY = '\nPlease use nightly transformers via pip install --upgrade "transformers>=4.49.0"`'
|
||||
# Pixtral
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue