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

12
llama_stack/providers/inline/inference/meta_reference/inference.py
View file

@ -31,23 +31,21 @@ from llama_stack.apis.inference import (
LogProbConfig,
Message,
ResponseFormat,
SamplingParams,
StopReason,
TokenLogProbs,
ToolChoice,
ToolConfig,
)
from llama_stack.apis.models import Model, ModelType
from llama_stack.models.llama.datatypes import (
ModelFamily,
SamplingParams,
StopReason,
ToolDefinition,
ToolPromptFormat,
)
from llama_stack.apis.models import Model, ModelType
from llama_stack.models.llama.llama3.chat_format import ChatFormat as Llama3ChatFormat
from llama_stack.models.llama.llama3.tokenizer import Tokenizer as Llama3Tokenizer
from llama_stack.models.llama.llama4.chat_format import ChatFormat as Llama4ChatFormat
from llama_stack.models.llama.llama4.tokenizer import Tokenizer as Llama4Tokenizer
from llama_stack.models.llama.sku_list import resolve_model
from llama_stack.models.llama.sku_types import ModelFamily
from llama_stack.providers.datatypes import ModelsProtocolPrivate
from llama_stack.providers.utils.inference.embedding_mixin import (
SentenceTransformerEmbeddingMixin,
@ -151,7 +149,7 @@ class MetaReferenceInferenceImpl(
if self.config.create_distributed_process_group:
self.generator = LlamaModelParallelGenerator(
model_parallel_size=llama_model.pth_file_count,
model_parallel_size=self.config.model_parallel_size or llama_model.pth_file_count,
builder_fn=builder_fn,
builder_params=builder_params,
formatter=(