Source: github.com/wudixzy/competition (1527 files, BI-V100 competition reference)
Imported assets:
- 12 prebuilt CoreX .so extensions (corex-3.2.3-ivcore10):
corex_gdn_{beta_decay,causal_conv,gated_norm,packed_decode,qk_map}.so
corex_moe_{direct_routed,exact_reduce,weight_gather}.so
corex_attn_head_rms_norm.so, corex_paged_kv_gather.so
corex_block_major_kv_transfer.so, corex_fused_paged_prefill.so
- 13 CUDA kernel sources (.cu) for above extensions
- 11 build scripts (build_corex_*.sh)
- install_prebuilt_corex.sh (SHA256-verified .so deployment)
- qwen3_5.py (2615 lines) with FULL corex kernel integration
- 9 vllm vendor override files (block manager, sampler, etc)
- 19 patch scripts (model_runner, xformers, block_major, etc)
- Complete serving layer (serving_chat, protocol, api_server, etc)
- bi100_env.py, bi100_profile.py, gdn_prefix.py, block_major_kv_cache.py
- Dockerfile aligned with reference build chain
- computility-run.yaml with BI100_MOE_COREX_DIRECT_ROUTED=1
Call chain verified:
Dockerfile COPY → patch_ops.sh → install_prebuilt_corex.sh → 12 .so to $VLLM_ROOT
qwen3_5.py imports: from vllm import corex_gdn_* / corex_moe_* / corex_attn_*
74 lines
2.8 KiB
Python
74 lines
2.8 KiB
Python
"""
|
|
Patches the vLLM model registry and deploys the Qwen3_5 model file.
|
|
|
|
Deploy steps on the remote machine:
|
|
1. patch_ops.sh locates vLLM with importlib.util.find_spec.
|
|
2. cp modified_scripts/qwen3_5.py into the detected vllm model directory.
|
|
2. python3 modified_scripts/patch_vllm_qwen3_5.py
|
|
|
|
The registry patch installs Qwen3.6 aliases so /model/config.json does not
|
|
need to be edited by hand.
|
|
"""
|
|
|
|
import ast
|
|
|
|
from patch_utils import package_root, replace_once
|
|
|
|
VLLM_ROOT = package_root("vllm")
|
|
REGISTRY = VLLM_ROOT / "model_executor" / "models" / "registry.py"
|
|
MODEL = VLLM_ROOT / "model_executor" / "models" / "qwen3_5.py"
|
|
|
|
EXPECTED_REGISTRY_ENTRIES = (
|
|
'"Qwen3ForCausalLM": ("qwen3_5", "Qwen3_5ForCausalLM")',
|
|
'"Qwen3MoeForCausalLM": ("qwen3_5", "Qwen3_5MoeForCausalLM")',
|
|
'"Qwen3_5ForCausalLM": ("qwen3_5", "Qwen3_5ForCausalLM")',
|
|
'"Qwen3_5MoeForCausalLM": ("qwen3_5", "Qwen3_5MoeForCausalLM")',
|
|
'"Qwen3_6ForCausalLM": ("qwen3_5", "Qwen3_5ForCausalLM")',
|
|
'"Qwen3_6MoeForCausalLM": ("qwen3_5", "Qwen3_5MoeForCausalLM")',
|
|
)
|
|
|
|
|
|
def main():
|
|
print(f"=== Patching {REGISTRY} ===")
|
|
replace_once(
|
|
REGISTRY,
|
|
' "Qwen3ForCausalLM": ("qwen3", "Qwen3ForCausalLM"),\n'
|
|
' "Qwen3MoeForCausalLM": ("qwen3_moe", "Qwen3MoeForCausalLM"),',
|
|
' "Qwen3ForCausalLM": ("qwen3_5", "Qwen3_5ForCausalLM"),\n'
|
|
' "Qwen3MoeForCausalLM": ("qwen3_5", "Qwen3_5MoeForCausalLM"),\n'
|
|
' "Qwen3_5ForCausalLM": ("qwen3_5", "Qwen3_5ForCausalLM"),\n'
|
|
' "Qwen3_5MoeForCausalLM": ("qwen3_5", "Qwen3_5MoeForCausalLM"),\n'
|
|
' "Qwen3_6ForCausalLM": ("qwen3_5", "Qwen3_5ForCausalLM"),\n'
|
|
' "Qwen3_6MoeForCausalLM": ("qwen3_5", "Qwen3_5MoeForCausalLM"),',
|
|
required=True,
|
|
already_contains='"Qwen3_6MoeForCausalLM"')
|
|
|
|
print("\n=== Static verification ===")
|
|
model_source = MODEL.read_text(encoding="utf-8")
|
|
tree = ast.parse(model_source, filename=str(MODEL))
|
|
class_names = {
|
|
node.name for node in tree.body if isinstance(node, ast.ClassDef)
|
|
}
|
|
required_classes = {"Qwen3_5ForCausalLM", "Qwen3_5MoeForCausalLM"}
|
|
missing_classes = required_classes - class_names
|
|
if missing_classes:
|
|
raise RuntimeError(
|
|
f"Qwen3.5 model classes missing: {sorted(missing_classes)}")
|
|
|
|
registry_source = REGISTRY.read_text(encoding="utf-8")
|
|
missing_entries = [
|
|
entry for entry in EXPECTED_REGISTRY_ENTRIES
|
|
if entry not in registry_source
|
|
]
|
|
if missing_entries:
|
|
raise RuntimeError(
|
|
f"Qwen3.5 registry entries missing: {missing_entries}")
|
|
print(" model syntax and class declarations verified without import")
|
|
print(f" registry aliases verified: {len(EXPECTED_REGISTRY_ENTRIES)}")
|
|
|
|
print("\nDone. Registry aliases installed; do not edit /model/config.json.")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|