phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-27 18:50:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: move all llama code to models/llama out of meta reference (#1887)

Browse source 
# What does this PR do?

Move around bits. This makes the copies from llama-models _much_ easier
to maintain and ensures we don't entangle meta-reference specific
tidbits into llama-models code even by accident.

Also, kills the meta-reference-quantized-gpu distro and rolls
quantization deps into meta-reference-gpu.

## Test Plan

```
LLAMA_MODELS_DEBUG=1 \
  with-proxy llama stack run meta-reference-gpu \
  --env INFERENCE_MODEL=meta-llama/Llama-4-Scout-17B-16E-Instruct \
   --env INFERENCE_CHECKPOINT_DIR=<DIR> \
   --env MODEL_PARALLEL_SIZE=4 \
   --env QUANTIZATION_TYPE=fp8_mixed
```

Start a server with and without quantization. Point integration tests to
it using:

```
pytest -s -v  tests/integration/inference/test_text_inference.py \
   --stack-config http://localhost:8321 --text-model meta-llama/Llama-4-Scout-17B-16E-Instruct
```
This commit is contained in:
Ashwin Bharambe 2025-04-07 15:03:58 -07:00 • committed by GitHub
parent c52ccc4bbd
commit 530d4bdfe1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
85 changed files with 1267 additions and 1683 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/cli/download.py
View file

@ -29,8 +29,8 @@ from rich.progress import (
from termcolor import cprint
from llama_stack.cli.subcommand import Subcommand
from llama_stack.models.llama.datatypes import Model
from llama_stack.models.llama.sku_list import LlamaDownloadInfo
from llama_stack.models.llama.sku_types import Model
class Download(Subcommand):

11
llama_stack/cli/model/describe.py
View file

@ -63,17 +63,6 @@ class ModelDescribe(Subcommand):
("Model params.json", json.dumps(model.arch_args, indent=4)),
]
if model.recommended_sampling_params is not None:
sampling_params = model.recommended_sampling_params.model_dump()
for k in ("max_tokens", "repetition_penalty"):
del sampling_params[k]
rows.append(
(
"Recommended sampling params",
json.dumps(sampling_params, indent=4),
)
)
print_table(
rows,
headers,

2
llama_stack/cli/model/prompt_format.py
View file

@ -11,7 +11,7 @@ from pathlib import Path
from llama_stack.cli.subcommand import Subcommand
from llama_stack.cli.table import print_table
from llama_stack.models.llama.datatypes import CoreModelId, ModelFamily, is_multimodal, model_family
from llama_stack.models.llama.sku_types import CoreModelId, ModelFamily, is_multimodal, model_family
ROOT_DIR = Path(__file__).parent.parent.parent

5
llama_stack/cli/model/safety_models.py
View file

@ -4,12 +4,12 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from typing import Any, Dict, Optional
from typing import Any, Dict
from pydantic import BaseModel, ConfigDict, Field
from llama_stack.models.llama.datatypes import CheckpointQuantizationFormat, SamplingParams
from llama_stack.models.llama.sku_list import LlamaDownloadInfo
from llama_stack.models.llama.sku_types import CheckpointQuantizationFormat
class PromptGuardModel(BaseModel):
@ -23,7 +23,6 @@ class PromptGuardModel(BaseModel):
is_instruct_model: bool = False
quantization_format: CheckpointQuantizationFormat = CheckpointQuantizationFormat.bf16
arch_args: Dict[str, Any] = Field(default_factory=dict)
recommended_sampling_params: Optional[SamplingParams] = None
def descriptor(self) -> str:
return self.model_id