llama-stack-mirror

1716 commits 57 branches 151 tags 128 MiB

Author	SHA1	Message	Date
jiawenliu64	5ecedc12e7	clean up	2025-04-09 14:55:30 -07:00
jiawenliu64	c8a0b110c0	fix: on-the-fly int4 quantize parameter Before this PR: ``` [rank1]: TypeError: quantize_int4() got multiple values for argument 'output_device' ```	2025-04-09 13:35:11 -07:00
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

Author

SHA1

Message

Date

jiawenliu64

5ecedc12e7

clean up

2025-04-09 14:55:30 -07:00

jiawenliu64

c8a0b110c0

fix: on-the-fly int4 quantize parameter

Before this PR:
```
[rank1]: TypeError: quantize_int4() got multiple values for argument 'output_device'
```

2025-04-09 13:35:11 -07:00

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

Renamed from llama_stack/providers/inline/inference/meta_reference/llama4/quantization/loader.py (Browse further)

3 commits