e0344b1730
Root cause: When tool_choice=auto + tools present, the model enters <think>...</think> mode by default. On BI-V100 hardware, decode is slow enough that thinking consumes the entire max_tokens budget, and the model finishes (finish=stop) before ever emitting <tool_call> XML. Sub168 reference: d03 in 2.12s with tools=1, finish=tool_calls Our sub509: d03 in 49.04s with tools=0, finish=stop — FAIL Fix: Two-layer defense: 1. protocol.py normalize_messages: when tools active + tool_choice=auto and thinking not explicitly set, auto-set enable_thinking=False 2. qwen3coder_tool_parser.py adjust_request: same logic as defense-in-depth 3. baseline.muh synced with actual computility-run.yaml
46 lines
1.5 KiB
Plaintext
46 lines
1.5 KiB
Plaintext
# baseline.muh — Competition vllm launch configuration
|
|
# SYNCED FROM computility-run.yaml (the actual deployment config)
|
|
#
|
|
# This file stores ONLY the vllm server launch config.
|
|
# Kernel tuning values live in muh/include/muh/tuning/tuning_*.cuh
|
|
# as constexpr structs — NOT here.
|
|
#
|
|
# Pipeline:
|
|
# muh/tuning/*.cuh (bi100_* values) → gen_patch.py → vllm kernel patches
|
|
# baseline.muh (vllm config) → gen_yaml.py → computility-run.yaml
|
|
#
|
|
# CRITICAL: computility-run.yaml is the deployment source of truth.
|
|
# This .muh must stay in sync with it.
|
|
|
|
# --- vllm launch configuration ---
|
|
vllm:
|
|
model_path: /model
|
|
served_model_name: llm
|
|
max_model_len: 100000
|
|
gpu_memory_utilization: 0.90
|
|
tensor_parallel: 4
|
|
max_num_seqs: 1
|
|
trust_remote_code: true
|
|
disable_log_requests: true
|
|
disable_frontend_multiprocessing: true
|
|
enable_auto_tool_choice: true
|
|
tool_call_parser: qwen3_coder
|
|
reasoning_parser: qwen3
|
|
enable_prefix_caching: true
|
|
enforce_eager: true
|
|
dtype: half
|
|
|
|
concurrency: 1
|
|
|
|
env:
|
|
VLLM_ENGINE_ITERATION_TIMEOUT_S: 3600
|
|
VLLM_ATTENTION_BACKEND: XFORMERS
|
|
ENABLE_CUSTOM_IPC: 1
|
|
PYTHONPATH: /usr/local/corex/lib/python3/dist-packages:/usr/local/corex/lib64/python3/dist-packages
|
|
LD_LIBRARY_PATH: /usr/local/corex/lib64:/usr/local/openmpi/lib
|
|
VLLM_COREX_FA2_LIBRARY: /usr/local/corex/lib64/libcorex_fa2.so
|
|
VLLM_COREX_GDN_LIBRARY: /usr/local/corex/lib64/libcorex_gdn.so
|
|
VLLM_COREX_MOE_LIBRARY: /usr/local/corex/lib64/libcorex_moe.so
|
|
VLLM_REQUEST_METRICS_FILE: /tmp/vllm-request-metrics.jsonl
|
|
VLLM_CACHE_BLOCK_SIZE: 16
|