945c8aeb10
* fix: saving clones state dict
* fix: apply fix for only CP mode
* fix: add dropout check when using lora target param
* fix: re-add patch from transformers PR #39866
* feat: add moe quant to test by ved
* fix: try match target param properly end with
* fix: clear cache per param quant
* fix: attempt on-load quantize experts instead of post-load
* fix: attempt disable async load
* chore: add log
* chore: adjust log
* fix: remove cuda alloc for moe and enable async load
* chore: remove leftover logs
* chore: add extra empty cache
* fix(doc): clarify support
* fix: handle fsdp2 for paramwrapper dtensor
* feat: attempt to quant experts in 8bit mode too
* feat: attempt to release bf16 experts from vram
* feat: upgrade cce
* fix: fsdp2 init_sharded_param load int8/uint4 dtensor as
require_grad=true on init
* fix: remove unnecessary gc and empty cache
* Revert "fix: remove unnecessary gc and empty cache"
This reverts commit 1d54518990.
* fix: do not call full_tensor on non-dtensors
* fix: attempt to address fsdp2 with quant exp high loss
* fix: attempt lora quant experts wrong dim
* fix: ensure require_grad patch applied for lora 8bit
* fix: attempt lora 8bit fsdp2
* fix: attribute access on save for lora 8bit fsdp2
* fix: wrong weight attrib access
* chore(refactor): add config, re-arrange position of patches, clean
comments
* feat: add example docs
* chore: cherry pick trinity fixes from PR 3399
* chore: comments refactor; add guards
* fix: guard using wrong key
* fix: mamba save does not accept main process param
* fix: guard prevent double hook
* fix: move gc to upper scope
* chore: add comment on proxy forward patch
* fix: add comment to clarify
* feat: add test idempotency
* fix: AttributeError: `e_score_correction_bias` is not an nn.Parameter
* fix: AttributeError: 'NoneType' object has no attribute 'to'
* fix: update docs on cpu_ram_efficient_loading
34 lines
874 B
Python
34 lines
874 B
Python
"""Script to output the correct installation command for cut-cross-entropy."""
|
|
|
|
import importlib.util
|
|
import sys
|
|
|
|
try:
|
|
import torch
|
|
except ImportError as exc:
|
|
raise ImportError("Install torch via `pip install torch`") from exc
|
|
from packaging.version import Version as V
|
|
|
|
USE_UV = "--uv" in sys.argv[1:]
|
|
|
|
v = V(torch.__version__)
|
|
|
|
# no cut-cross-entropy support for torch < 2.4.0
|
|
if v < V("2.4.0"):
|
|
print("")
|
|
sys.exit(0)
|
|
|
|
cce_spec = importlib.util.find_spec("cut_cross_entropy")
|
|
|
|
UNINSTALL_PREFIX = ""
|
|
if cce_spec:
|
|
if not importlib.util.find_spec("cut_cross_entropy.transformers"):
|
|
UNINSTALL_PREFIX = "pip uninstall -y cut-cross-entropy && "
|
|
|
|
UV_PREFIX = "uv " if USE_UV else ""
|
|
|
|
print(
|
|
UNINSTALL_PREFIX
|
|
+ f'{UV_PREFIX}pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@a668583"'
|
|
)
|