llama-stack/llama_stack/models/llama/llama3/quantization/__init__.py at 530d4bdfe130ace4b31f09cb0334195928d4bc08 - phoenix-oss/llama-stack - Git for basel.kvant.cloud

phoenix-oss/llama-stack

forked from phoenix-oss/llama-stack-mirror

Ashwin Bharambe 530d4bdfe1

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

# 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
```

2025-04-07 15:03:58 -07:00

5 lines

200 B

Python

Raw Blame History

 # Copyright (c) Meta Platforms, Inc. and affiliates.
 # All rights reserved.
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.