huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 03:44:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Apply suggestions from code review

Browse Source 
Co-authored-by: OlivierDehaene <olivier@huggingface.co>
This commit is contained in:
Nicolas Patry 2023-06-07 14:59:29 +02:00 committed by GitHub
parent c6ac50e42b
commit 6ddcd1582c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 0 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Dockerfile
View File

@ -105,7 +105,6 @@ WORKDIR /usr/src
COPY server/custom_kernels/ .
# Build specific version of transformers
RUN pip install ninja
RUN python setup.py build
# Text Generation Inference base image
@ -137,7 +136,6 @@ COPY --from=flash-att-builder /usr/src/flash-attention/csrc/layer_norm/build/lib
COPY --from=flash-att-builder /usr/src/flash-attention/csrc/rotary/build/lib.linux-x86_64-cpython-39 /opt/conda/lib/python3.9/site-packages
# Copy build artifacts from transformers builder
COPY --from=custom-kernels-builder /usr/src/custom_kernels /usr/src/custom_kernels
COPY --from=custom-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-39/custom_kernels /usr/src/custom-kernels/src/custom_kernels
# Install transformers dependencies

1
server/text_generation_server/models/__init__.py
View File

@ -54,7 +54,6 @@ __all__ = [
"BLOOMSharded",
"CausalLM",
"FlashCausalLM",
"Galactica",
"GalacticaSharded",
"Seq2SeqLM",
"SantaCoder",

5
server/text_generation_server/models/custom_modeling/flash_llama_modeling.py
View File

@ -301,14 +301,9 @@ class FlashLlamaModel(torch.nn.Module):
self.layers = nn.ModuleList(
[
FlashLlamaLayer(
# config.num_attention_heads,
# config.hidden_act,
# config.hidden_size,
# config.intermediate_size,
layer_id,
config,
weights,
# config.rms_norm_eps,
)
for layer_id in range(config.num_hidden_layers)
]