huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-19 22:02:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

Hotfixing intel-cpu (not sure how it was working before). (#2967)

Browse Source 
* Hotfixing intel-cpu (not sure how it was working before).

* Do not fail on missing moe-kernels (Intel-cpu).
This commit is contained in:
Nicolas Patry 2025-01-29 22:34:41 +01:00 committed by GitHub
parent ee0dffcd14
commit 80e7d98f88
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
server/text_generation_server/layers/moe/fp8.py
View File

@ -10,7 +10,11 @@ from text_generation_server.layers.fp8 import (
quant_dtype, quant_dtype,
normalize_e4m3fn_to_native_float8, normalize_e4m3fn_to_native_float8,
) )
from moe_kernels.fused_moe import fused_moe
try:
from moe_kernels.fused_moe import fused_moe
except Exception:
fused_moe = None
class FP8SparseMoELayer(nn.Module): class FP8SparseMoELayer(nn.Module):

2
server/text_generation_server/models/__init__.py
View File

@ -180,7 +180,7 @@ except ImportError as e:
if MAMBA_AVAILABLE: if MAMBA_AVAILABLE:
__all__.append(Mamba) __all__.append(Mamba)
FLASH_TRANSFORMERS_BACKEND = True FLASH_TRANSFORMERS_BACKEND = torch.cuda.is_available()
try: try:
from text_generation_server.models.transformers_flash_causal_lm import ( from text_generation_server.models.transformers_flash_causal_lm import (
TransformersFlashCausalLM, TransformersFlashCausalLM,