huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 12:24:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Apply suggestions from code review

Browse Source 
Co-authored-by: Mohit Sharma <mohit21sharma.ms@gmail.com>
This commit is contained in:
Nicolas Patry 2025-01-30 11:59:12 +01:00 committed by GitHub
parent 9376066b24
commit f56e24b346
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Dockerfile_amd
View File

@ -279,9 +279,9 @@ RUN git clone https://github.com/danieldk/marlin-kernels.git && \
FROM kernel-builder AS moe-kernels FROM kernel-builder AS moe-kernels
WORKDIR /usr/src WORKDIR /usr/src
ENV MOE_KERNELS_BRANCH=9fb72ccb00b8da96a41f9b9c48f305c7dbd266bc ENV MOE_KERNELS_BRANCH=d7e042bf9f7aff10c631212fc71b24895d66eb59
ENV VLLM_TARGET_DEVICE=rocm ENV VLLM_TARGET_DEVICE=rocm
RUN git clone https://github.com/mht-sharma/moe-kernels.git && \ RUN git clone https://github.com/danieldk/moe-kernels.git && \
cd moe-kernels && \ cd moe-kernels && \
git checkout ${MOE_KERNELS_BRANCH} && \ git checkout ${MOE_KERNELS_BRANCH} && \
python setup.py install python setup.py install

2
server/text_generation_server/layers/moe/unquantized.py
View File

@ -73,8 +73,6 @@ class UnquantizedSparseMoELayer(nn.Module):
num_expert_group=self.n_expert_group, num_expert_group=self.n_expert_group,
topk_group=self.topk_group, topk_group=self.topk_group,
) )
# from loguru import logger
# logger.info("Fused MoE is used here")
return fused_moe( return fused_moe(
x, x,
w1=self.gate_up_proj, w1=self.gate_up_proj,