biondizzle/deepseek-v4-quant
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docker: add OMP_NUM_THREADS=64, remove --tool initcheck, mount cubin cache

Browse Source
This commit is contained in:
biondizzle
2026-05-12 11:15:06 +00:00
parent 5840291ea3
commit b8f95ffad3
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docker-compose.yml
View File

@@ -11,6 +11,7 @@ services:
- --
environment:
- HF_TOKEN=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
- OMP_NUM_THREADS=64
command:
- /model
- --trust-remote-code
@@ -21,9 +22,7 @@ services:
- --compilation-config={"cudagraph_mode":"FULL_AND_PIECEWISE","custom_ops":["all"]}
- --attention_config.use_fp4_indexer_cache=True
- --tokenizer-mode=deepseek_v4
- --tool-call-parser=deepseek_v4
- --enable-auto-tool-choice
- --reasoning-parser=deepseek_v4
- --speculative_config={"method":"mtp","num_speculative_tokens":2}
- --host=0.0.0.0
- --port=8000
@@ -43,4 +42,5 @@ services:
- /root/nvidia-meeting/DeepSeek-V4-Pro-NVFP4:/model:ro
- /root/nvidia-meeting/deepseek-v4-quant/patches/deepseek_v4.py:/patches/deepseek_v4.py:ro
- /root/nvidia-meeting/deepseek-v4-quant/patches:/patches:ro
- /srv/vllmcache:/root/.cache/vllm/deep_gemm/cache
network_mode: host