Skip to content

feat: enable FP8 quantized models loading #316

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 8 commits into
base: main
Choose a base branch
from
+3 −1
Open

feat: enable FP8 quantized models loading #316

Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
29f7021
Some updates for quant testing
rafvasq Jul 16, 2025
5efcfaa
Add fp8 config loading
rafvasq Jul 22, 2025
2df1c23
Lint
rafvasq Jul 22, 2025
dfd2376
Refactor
rafvasq Jul 22, 2025
9762f56
Update tests
rafvasq Jul 22, 2025
e541cc8
Lint
rafvasq Jul 22, 2025
bb17bbf
Add comment
rafvasq Jul 23, 2025
b115b6b
Revert for clarity
rafvasq Jul 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion vllm_spyre/platform.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,9 @@ class SpyrePlatform(Platform):
# "spyre" device_name no longer worked due to https://github.com/vllm-project/vllm/pull/16464
device_name: str = "cpu"
device_type: str = "cpu"
supported_quantization: list[str] = ["gptq"]
# compressed-tensors supported by
# https://github.com/foundation-model-stack/fms-model-optimizer/blob/main/fms_mo/aiu_addons/__init__.py
supported_quantization: list[str] = ["gptq", "compressed-tensors"]
_warmup_shapes: Optional[tuple[dict[str, int], ...]] = None
_block_size: int = 64 # hardcoded Spyre constraint for now
_config: VllmConfig = None
Expand Down
Loading