project_6/baseline.muh

# baseline.muh — Competition vllm launch configuration
#
# 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

# --- vllm launch configuration ---
vllm:
  model_path: /model
  served_model_name: llm
  max_model_len: 100000
  gpu_memory_utilization: 0.9
  tensor_parallel: 4
  max_num_seqs: 1
  max_num_batched_tokens: 8192
  max_seq_len_to_capture: 32768
  trust_remote_code: true
  disable_log_requests: true
  disable_frontend_multiprocessing: true
  enable_chunked_prefill: true
  enable_auto_tool_choice: true
  tool_call_parser: qwen3_coder
  reasoning_parser: qwen3
  enable_prefix_caching: true

concurrency: 1

env:
  VLLM_ENGINE_ITERATION_TIMEOUT_S: 3600
[MUH] Fix three-layer disconnect — C++ headers are now the single source of truth Problems fixed: 1. gen_patch.py was reading .muh YAML (all nulls) instead of C++ headers. Now it parses bi100_* structs directly from tuning_.cuh via regex, extracts constexpr values, and maps them to vllm injection points. Verified: 11 patches generated from 6 algorithms. 2. C++ headers had no build system or tests. Added CMakeLists.txt (header-only library target) and compile_test.cpp. Verified: g++ -std=c++17 compiles all headers, 17/17 runtime checks pass. Also added cuda_compile_test.cu for when nvcc is available. 3. baseline.muh had a tuning section full of nulls duplicating C++ values. Stripped to vllm launch config only. Tuning values live exclusively in muh/include/muh/tuning/tuning_.cuh bi100_* structs. 4. Fixed constexpr goto in tuning_scan.cuh (C++17 doesn't allow goto in constexpr; replaced with early-return + default: break pattern). Data flow is now: tuning_.cuh (bi100_ constexpr) ──→ gen_patch.py ──→ vllm patches baseline.muh (launch config) ──→ gen_yaml.py ──→ computility-run.yaml compile_test.cpp ──→ g++/nvcc ──→ verify values are real 2026-07-30 14:12:33 +00:00			`# baseline.muh — Competition vllm launch configuration`
[MUH] Bootstrap muh toolchain — extract/parse/gen_yaml/gen_patch + baseline.muh Pipeline: 1. extract.py: Parses all 26 CCCL tuning_*.cuh → 26 YAML schemas in muh/schema/ 2. parse.py: .muh file parser with extends-inheritance + schema validation 3. gen_yaml.py: .muh → computility-run.yaml (verified: matches competition reference) 4. gen_patch.py: .muh → vllm kernel unified diff patches (6 algorithm mappings) 5. baseline.muh: Competition reference config, all tuning values pending BI-V100 benchmarks Schemas extracted: 26 algorithms, 8-19 params each, SM75/80/90/100 reference tunings Priority mapping: reduce→attention, topk→sampling, scan→paged_attention, transform→activations, batch_memcpy→KV_cache, for→RoPE Tested: extract→parse→validate→gen_yaml→gen_patch full pipeline passes 2026-07-30 10:39:06 +00:00			`#`
[MUH] Fix three-layer disconnect — C++ headers are now the single source of truth Problems fixed: 1. gen_patch.py was reading .muh YAML (all nulls) instead of C++ headers. Now it parses bi100_* structs directly from tuning_.cuh via regex, extracts constexpr values, and maps them to vllm injection points. Verified: 11 patches generated from 6 algorithms. 2. C++ headers had no build system or tests. Added CMakeLists.txt (header-only library target) and compile_test.cpp. Verified: g++ -std=c++17 compiles all headers, 17/17 runtime checks pass. Also added cuda_compile_test.cu for when nvcc is available. 3. baseline.muh had a tuning section full of nulls duplicating C++ values. Stripped to vllm launch config only. Tuning values live exclusively in muh/include/muh/tuning/tuning_.cuh bi100_* structs. 4. Fixed constexpr goto in tuning_scan.cuh (C++17 doesn't allow goto in constexpr; replaced with early-return + default: break pattern). Data flow is now: tuning_.cuh (bi100_ constexpr) ──→ gen_patch.py ──→ vllm patches baseline.muh (launch config) ──→ gen_yaml.py ──→ computility-run.yaml compile_test.cpp ──→ g++/nvcc ──→ verify values are real 2026-07-30 14:12:33 +00:00			`# 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`
[MUH] Bootstrap muh toolchain — extract/parse/gen_yaml/gen_patch + baseline.muh Pipeline: 1. extract.py: Parses all 26 CCCL tuning_*.cuh → 26 YAML schemas in muh/schema/ 2. parse.py: .muh file parser with extends-inheritance + schema validation 3. gen_yaml.py: .muh → computility-run.yaml (verified: matches competition reference) 4. gen_patch.py: .muh → vllm kernel unified diff patches (6 algorithm mappings) 5. baseline.muh: Competition reference config, all tuning values pending BI-V100 benchmarks Schemas extracted: 26 algorithms, 8-19 params each, SM75/80/90/100 reference tunings Priority mapping: reduce→attention, topk→sampling, scan→paged_attention, transform→activations, batch_memcpy→KV_cache, for→RoPE Tested: extract→parse→validate→gen_yaml→gen_patch full pipeline passes 2026-07-30 10:39:06 +00:00
			`# --- vllm launch configuration ---`
			`vllm:`
			`model_path: /model`
			`served_model_name: llm`
			`max_model_len: 100000`
			`gpu_memory_utilization: 0.9`
			`tensor_parallel: 4`
			`max_num_seqs: 1`
			`max_num_batched_tokens: 8192`
			`max_seq_len_to_capture: 32768`
			`trust_remote_code: true`
			`disable_log_requests: true`
			`disable_frontend_multiprocessing: true`
			`enable_chunked_prefill: true`
			`enable_auto_tool_choice: true`
			`tool_call_parser: qwen3_coder`
			`reasoning_parser: qwen3`
			`enable_prefix_caching: true`

			`concurrency: 1`

			`env:`
			`VLLM_ENGINE_ITERATION_TIMEOUT_S: 3600`