phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-02 17:54:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

rename quant types to use _mixed naming

Browse source
This commit is contained in:
Ashwin Bharambe 2025-04-07 12:57:58 -07:00
parent b239c57c54
commit 76004eacb4
3 changed files with 11 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/providers/inline/inference/meta_reference/generators.py
View file

@ -133,9 +133,9 @@ class Llama4Generator:
ckpt_dir = model_checkpoint_dir(resolved_model.descriptor())
if config.quantization:
if config.quantization.type == "fp8":
if config.quantization.type == "fp8_mixed":
quantization_mode = QuantizationMode.fp8_mixed
elif config.quantization.type == "int4":
elif config.quantization.type == "int4_mixed":
quantization_mode = QuantizationMode.int4_mixed
elif config.quantization.type == "bf16":
quantization_mode = None
@ -226,9 +226,9 @@ class Llama3Generator:
ckpt_dir = model_checkpoint_dir(resolved_model.descriptor())
if config.quantization:
if config.quantization.type == "fp8":
if config.quantization.type == "fp8_mixed":
quantization_mode = QuantizationMode.fp8_mixed
elif config.quantization.type == "int4":
elif config.quantization.type == "int4_mixed":
quantization_mode = QuantizationMode.int4_mixed
elif config.quantization.type == "bf16":
quantization_mode = None