biondizzle
f74447bfd0
Weight mapper fixes: - Reorder substr renames: compressor renames first, then .self_attn.compressor. → .attn.mla_attn.compressor., then indexer renames (so indexer keys end up under mla_attn after the compressor rename already fired) - Add compressor param renames: kv_proj→wkv, gate_proj→wgate, kv_norm→norm, position_bias→ape (checkpoint uses NVFP4 naming, model uses internal names) - Add indexer param renames: q_b_proj→wq_b, kv_proj→compressor.wkv, gate_proj→compressor.wgate, kv_norm→k_norm, position_bias→compressor.ape, weights_proj stays (structural: compressor.indexer → indexer.compressor) - Remove broken suffix renames (already fixed in prior commit) Model architecture fixes: - Patch deepseek_compressor.py to pass quant_config (was None, but NVFP4 checkpoint has quantized compressor weights with input_scale/weight_scale) - Patch deepseek_v4_attention.py indexer: weights_proj now uses quant_config (was None, but checkpoint has quantized weights) - Add indexer.compressor.fused_wkv_wgate stacking in load_weights Infrastructure: - Add deepseek_compressor.py to Dockerfile - Force MoE backend to flashinfer_cutedsl (was auto-selecting FLASHINFER_TRTLLM) - Update unit test to 50 cases (compressor + indexer + quantization scales)
37 lines
969 B
YAML
37 lines
969 B
YAML
services:
|
|
vllm:
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile
|
|
ports:
|
|
- "8000:8000"
|
|
environment:
|
|
- OMP_NUM_THREADS=128
|
|
- CUDA_LAUNCH_BLOCKING=0
|
|
- PYTHONUNBUFFERED=1
|
|
- VLLM_RPC_TIMEOUT_MS=600000
|
|
- CLAWMINE_DEBUG=1
|
|
command:
|
|
- /model
|
|
- --trust-remote-code
|
|
- --enable-expert-parallel
|
|
- --tensor-parallel-size=8
|
|
- --compilation-config={"cudagraph_mode":"NONE","custom_ops":["all"]}
|
|
- --tokenizer-mode=deepseek_v4
|
|
- --tool-call-parser=deepseek_v4
|
|
- --enable-auto-tool-choice
|
|
- --reasoning-parser=deepseek_v4
|
|
- --moe-backend=flashinfer_cutedsl
|
|
- --gpu-memory-utilization=0.9
|
|
- --host=0.0.0.0
|
|
- --port=8000
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: all
|
|
capabilities: [gpu]
|
|
volumes:
|
|
- /root/nvidia-meeting/DeepSeek-V4-Pro-NVFP4:/model:ro
|