biondizzle/vllm-with-lmcache
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

lmcache config

Browse Source
This commit is contained in:
biondizzle
2026-05-05 09:27:48 +00:00
parent b1b957ada2
commit e043095aab
2 changed files with 11 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
Dockerfile
View File

@@ -43,4 +43,7 @@ RUN apt-get update && apt-get install -y git \
#COPY hf.py /usr/local/lib/python3.12/dist-packages/vllm/renderers/hf.py
# Make sure we have the latest up to date chat template
#COPY glm_5.1_chat_template.jinja /opt/chat_template.jinja
COPY glm_5.1_chat_template.jinja /opt/chat_template.jinja
# Working LMCache config
COPY lmcache-config.yaml /opt/lmcache-config.yaml

7
lmcache-config.yaml Normal file
View File

@@ -0,0 +1,7 @@
chunk_size: 256
local_cpu: true
max_local_cpu_size: 256.0
save_decode_cache: false
enable_lazy_memory_allocator: true
lazy_memory_initial_ratio: 1.0
use_gpu_connector_v3: true