phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

chore: remove dependency on llama_models completely (#1344)

Browse source
This commit is contained in:
Ashwin Bharambe 2025-03-01 12:48:08 -08:00 • committed by GitHub
parent 7131d5ddeb
commit 8bbd52bb9f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
43 changed files with 131358 additions and 202 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/inline/inference/meta_reference/quantization/loader.py
View file

@ -15,13 +15,13 @@ import torch
from fairscale.nn.model_parallel.initialize import get_model_parallel_rank
from fairscale.nn.model_parallel.layers import ColumnParallelLinear, RowParallelLinear
from fairscale.nn.model_parallel.mappings import reduce_from_model_parallel_region
from llama_models.llama3.api.args import ModelArgs
from llama_models.llama3.reference_impl.model import Transformer, TransformerBlock
from torch import Tensor, nn
from torchao.quantization.GPTQ import Int8DynActInt4WeightLinear
from llama_stack.apis.inference import QuantizationType
from llama_stack.models.llama.datatypes import CheckpointQuantizationFormat
from llama_stack.models.llama.llama3.args import ModelArgs
from llama_stack.models.llama.llama3.model import Transformer, TransformerBlock
from llama_stack.models.llama.sku_list import resolve_model
from ..config import MetaReferenceQuantizedInferenceConfig

6
llama_stack/providers/inline/inference/meta_reference/quantization/scripts/quantize_checkpoint.py
View file

@ -22,11 +22,11 @@ from fairscale.nn.model_parallel.initialize import (
initialize_model_parallel,
model_parallel_is_initialized,
)
from llama_models.llama3.api.args import ModelArgs
from llama_models.llama3.api.tokenizer import Tokenizer
from llama_models.llama3.reference_impl.model import Transformer, TransformerBlock
from torch.nn.parameter import Parameter
from llama_stack.models.llama.llama3.args import ModelArgs
from llama_stack.models.llama.llama3.model import Transformer, TransformerBlock
from llama_stack.models.llama.llama3.tokenizer import Tokenizer
from llama_stack.providers.inline.inference.meta_reference.quantization.fp8_impls import (
quantize_fp8,
)