phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-23 07:12:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: add auto-generated CI documentation pre-commit hook (#2890)

Browse source 
Our CI is entirely undocumented, this commit adds a README.md file with
a table of the current CI and what is does

---------

Signed-off-by: Nathan Weinberg <nweinber@redhat.com>
This commit is contained in:
Nathan Weinberg 2025-07-25 11:57:01 -04:00 • committed by Mustafa Elbehery
parent 7f834339ba
commit b381ed6d64
93 changed files with 495 additions and 477 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_stack/models/llama/quantize_impls.py
View file

@ -6,16 +6,17 @@
# type: ignore
import collections
import logging
log = logging.getLogger(__name__)
from llama_stack.log import get_logger
logger = get_logger(__name__, category="core")
try:
import fbgemm_gpu.experimental.gen_ai # noqa: F401
log.info("Using efficient FP8 or INT4 operators in FBGEMM.")
logger.info("Using efficient FP8 or INT4 operators in FBGEMM.")
except ImportError:
log.error("No efficient FP8 or INT4 operators. Please install FBGEMM.")
logger.error("No efficient FP8 or INT4 operators. Please install FBGEMM.")
raise
import torch