Skip to content

Commit

Permalink
Merge branch 'habana_main' into benchmark_image
Browse files Browse the repository at this point in the history
  • Loading branch information
kdamaszk authored Jan 27, 2025
2 parents d6ccd31 + 107a9a3 commit 72f5077
Show file tree
Hide file tree
Showing 2 changed files with 2 additions and 2 deletions.
2 changes: 1 addition & 1 deletion docs/source/features/quantization/supported_hardware.md
Original file line number Diff line number Diff line change
Expand Up @@ -76,7 +76,7 @@ The table below shows the compatibility of various quantization implementations
- ✅︎
- ✅︎
- ✗
-
- ✅︎
- ✗
- ✗
- ✗
Expand Down
2 changes: 1 addition & 1 deletion vllm/platforms/hpu.py
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ class HpuPlatform(Platform):
dispatch_key: str = "HPU"
ray_device_key: str = "HPU"
device_control_env_var: str = "HABANA_VISIBLE_MODULES"
supported_quantization: list[str] = ["inc"]
supported_quantization: list[str] = ["fp8", "inc"]

@classmethod
def get_attn_backend_cls(cls, selected_backend: _Backend, head_size: int,
Expand Down

0 comments on commit 72f5077

Please sign in to comment.