sync B200 deployment files: Dockerfile, docker-compose, patches

docker-compose.yml

@@ -1,30 +1,22 @@
 services:
   vllm:
-    image: atl.vultrcr.com/vllm/vllm-with-lmcache:dream-build
-    pull_policy: always
-    entrypoint:
-      - bash
-      - -c
-      - |
-        cp /patches/deepseek_v4.py /usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/deepseek_v4.py
-        exec vllm serve "$$@"
-      - --
+    build:
+      context: .
+    ports:
+      - "8000:8000"
     environment:
-      - HF_TOKEN=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
+      - OMP_NUM_THREADS=128
+      - MEGA_MOE_DEBUG=1
+      - MEGA_MOE_STATIC=0
+      - MEGA_MOE_USE_CUTLASS=1
+      - DG_JIT_DEBUG=1
     command:
       - /model
       - --trust-remote-code
-      - --kv-cache-dtype=fp8
-      - --block-size=256
       - --enable-expert-parallel
       - --tensor-parallel-size=8
-      - --compilation-config={"cudagraph_mode":"FULL_AND_PIECEWISE","custom_ops":["all"]}
-      - --attention_config.use_fp4_indexer_cache=True
+      - --enforce-eager
       - --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
     deploy:
@@ -34,13 +26,5 @@ services:
             - driver: nvidia
               count: all
               capabilities: [gpu]
-    ipc: host
-    security_opt:
-      - seccomp:unconfined
-    tty: true
-    stdin_open: true
     volumes:
       - /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
-    network_mode: host