Home / eugr / spark-vllm-docker
AI Slop Code RIsk Monitor

eugr/spark-vllm-docker

Docker configuration for running VLLM on dual DGX Sparks

15.1 Elevated pattern signal View on GitHub

Maintenance and Governance Review

This report summarizes scanner evidence for eugr/spark-vllm-docker, a Python project with 2,378 GitHub stars. SynthScan examined 32,408 lines of code across 164 source files, recording 419 pattern matches distributed across 14 syntactic categories. The legacy adjusted pattern signal is 15.1 (Elevated pattern signal); it is not an authorship estimate.

Use the findings to ask whether maintainers can explain intent, verify dependencies, simplify unnecessary scaffolding, and focus review effort. Risk Payload v1 adds ownership, supply-chain, over-engineering, and review-effort vectors when available. These are prompts for human verification, not probabilities, security findings, or measured maintenance costs.

15.1
Adjusted Signal
15.1
Raw Pattern Score
100%
Time Factor
2026-10-09
Last Push
2.4K
Stars
Python
Language
32.4K
Lines of Code
164
Files
419
Pattern Hits
2026-10-12
Scan Date
0.04
HC Hit Rate

Risk Review · v3

Use each vector to guide manual verification of the underlying findings.

Cognitive Ownership Risk 38.7/100 · MEDIUM

Can maintainers explain intent, assumptions, and trade-offs? 337 finding(s).

Hallucinated Dependency & Supply Chain Risk 2.8/100 · LOW

Are imports declared and package/API names verified? 19 finding(s).

Agent Over-Engineering Ratio 44.2/100 · MEDIUM

Are wrappers, guards, and repeated structures necessary? 339 finding(s).

PR Review Velocity Impact 58.8/100 · HIGH

Which changes need focused human review? 419 finding(s).

What These Metrics Mean

Adjusted Signal
Legacy pattern score normalized per 1,000 scanned lines and multiplied by the repository-level time factor. It is not an estimate of AI authorship.
Raw Pattern Score
Sum of severity- and context-weighted pattern findings before applying the time factor.
Time Factor
A coarse multiplier based on repository last-push metadata. It does not identify when individual code was written.
Pattern Hits
Count of configured pattern findings. Review each location and surrounding code before acting.
HC Hit Rate
High- and critical-severity findings per scanned file. Severity is a configured detector weight, not proof of a vulnerability or authorship.
Lines / Files
Scan coverage denominators used by the legacy normalized score.

Pattern-Signal History

This chart tracks the legacy adjusted pattern score across scan runs. Changes can reflect source changes, scan coverage, or detector/scoring versions; they do not measure AI adoption or prove that a team refactored code. Compare runs only when their scoring versions are compatible. The dashed line tracks the raw pattern-hit count.

Severity Breakdown

Groups findings by configured severity weight. Severity is not a confidence estimate, security rating, or proof that a package is missing. Verify imports against the project's manifests and inspect each finding in its local design context.

CRITICAL 0HIGH 7MEDIUM 60LOW 352

Directory Score Breakdown

This horizontal bar chart shows where configured pattern scores accumulate across directories. Treat the bars as locations to inspect, not as evidence of authorship or code quality. Use the file-level findings to decide whether a directory needs a focused ownership, dependency, complexity, or review check.

Pattern Findings

The scanner identified 419 distinct pattern matches across 14 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.

Hyper-Verbose Identifiers275 hits · 223 pts
SeverityFileLineSnippetContext
LOWrun-recipe.py117def runtime_vllm_pr_reference(value: str) -> str:CODE
LOWrun-recipe.py154def strip_distributed_executor_backend(command: str) -> str:CODE
LOWdocker/patch_vllm_swa_block_size.py79 if "def _largest_kernel_block_within(" not in source:CODE
LOWdocker/patch_vllm_mrv2_speculator_cudagraph_pool.py80 "def _profiling_cudagraph_managers(",CODE
LOW⚡tests/test_instanttensor_vllm_memory_patch.py181 def test_vllm_available_memory_allows_large_tensor_despite_small_cuda_reading(self):STRING
LOW⚡tests/test_instanttensor_vllm_memory_patch.py189 def test_low_vllm_availability_still_rejects_oversized_buffers(self):STRING
LOW⚡tests/test_instanttensor_vllm_memory_patch.py197 def test_explicit_budget_fraction_and_boundary_are_preserved(self):STRING
LOW⚡tests/test_instanttensor_vllm_memory_patch.py204 def test_distributed_budget_is_still_the_minimum_across_ranks(self):STRING
LOW⚡tests/test_instanttensor_vllm_memory_patch.py212 def test_patch_is_scoped_and_idempotent_without_importing_packages(self):STRING
LOWtests/test_instanttensor_vllm_memory_patch.py233 def test_unknown_or_ambiguous_sources_fail_without_writing(self):STRING
LOWtests/test_instanttensor_vllm_memory_patch.py250 def test_runner_patches_after_dependency_installation(self):STRING
LOWtests/test_instanttensor_vllm_memory_patch.py266 def test_invalid_budget_participates_in_collective_before_raising(self):STRING
LOWtests/test_instanttensor_vllm_memory_patch.py303 def test_failed_remote_budget_still_rejects_local_load(self):STRING
LOW⚡tests/test_cluster_topology.py46 def test_ring_order_collapses_twin_rails(self):CODE
LOW⚡tests/test_cluster_topology.py51 def test_copy_paths_cover_opposite_node(self):CODE
LOW⚡tests/test_cluster_topology.py56 def test_launch_order_and_trim_validation(self):CODE
LOWtests/test_cluster_topology.py70 def test_invalid_and_disconnected_links(self):CODE
LOWtests/test_cluster_topology.py86 def test_multihop_ssh_config_is_parseable_and_temporary(self):CODE
LOWtests/test_cluster_topology.py100 def test_discovery_checks_remote_rails_in_both_directions(self):CODE
LOWtests/test_cluster_topology.py116 def test_larger_ring_discovery_and_launch_validation(self):CODE
LOW⚡tests/test_cluster_topology.py220 def test_image_inspection_and_stream_use_same_routes(self):STRING
LOW⚡tests/test_cluster_topology.py229 def test_model_permissions_and_rsync_use_same_routes(self):STRING
LOW⚡tests/test_cluster_topology.py238 def test_larger_ring_image_and_model_distribution(self):STRING
LOW⚡tests/test_cluster_topology.py278 def test_explicit_copy_subset_and_failure(self):STRING
LOW⚡tests/test_cluster_topology.py284 def test_launch_generates_ring_env_for_every_rank(self):STRING
LOW⚡tests/test_cluster_topology.py294 def test_invalid_launch_never_starts_or_stops_containers(self):STRING
LOW⚡tests/test_cluster_topology.py302 def test_discovery_saves_one_config_and_rejects_broken_selection(self):STRING
LOW⚡tests/test_cluster_topology.py378 def test_dry_run_rejects_bad_order_without_network(self):STRING
LOW⚡tests/test_cluster_topology.py388 def test_cached_model_is_distributed_to_every_ring_worker(self):STRING
LOW⚡tests/test_cluster_topology.py398 def test_existing_image_is_synced_without_building_for_ring(self):STRING
LOWtests/test_cluster_topology.py324 def test_legacy_two_node_triangle_and_switch_copy_selection(self):STRING
LOWtests/test_cluster_topology.py366 def test_config_forwarded_to_distribution_scripts(self):STRING
LOW…sts/test_flashinfer_b12x_loader_include_order_patch.py63 def test_broken_loader_fails_compilation_then_compiles_after_patch(self):CODE
LOW…sts/test_flashinfer_b12x_loader_include_order_patch.py76 def test_upstream_fixed_source_is_untouched(self):CODE
LOW⚡tests/test_hf_cache_management.py357 def test_uvx_installer_failure_aborts_before_deletion(self):STRING
LOW⚡tests/test_hf_cache_management.py366 def test_uvx_without_downloader_reports_actionable_error(self):STRING
LOW⚡tests/test_hf_cache_management.py373 def test_cluster_inventory_remote_only_revisions_sort_and_formats(self):STRING
LOW⚡tests/test_hf_cache_management.py434 def test_documented_download_argument_orders(self):STRING
LOW⚡tests/test_hf_cache_management.py444 def test_delete_confirmation_force_and_remote_only(self):STRING
LOW⚡tests/test_hf_cache_management.py453 def test_delete_yes_and_failure_propagation(self):STRING
LOW⚡tests/test_hf_cache_management.py460 def test_cleanup_preserves_refs_datasets_and_protected_hashes(self):STRING
LOW⚡tests/test_hf_cache_management.py552 def test_delete_revision_present_only_on_peer(self):STRING
LOW⚡tests/test_hf_cache_management.py559 def test_delete_branch_resolves_cached_commit(self):STRING
LOW⚡tests/test_hf_cache_management.py566 def test_unknown_and_ambiguous_revisions_never_delete(self):STRING
LOW⚡tests/test_hf_cache_management.py575 def test_revision_hash_collision_aborts_entire_cluster_delete(self):STRING
LOW⚡tests/test_hf_cache_management.py582 def test_backup_delete_revision_pins_heads_commit_and_preserves_peer_refs(self):STRING
LOW⚡tests/test_hf_cache_management.py600 def test_missing_backup_revision_does_not_publish_or_delete(self):STRING
LOW⚡tests/test_hf_cache_management.py607 def test_failed_backup_never_deletes_or_publishes(self):STRING
LOW⚡tests/test_hf_cache_management.py615 def test_backup_refuses_deleting_remote_revision_not_backed_up(self):STRING
LOW⚡tests/test_hf_cache_management.py623 def test_backup_delete_decline_keeps_backup_and_cache(self):STRING
LOW⚡tests/test_hf_cache_management.py630 def test_backup_refuses_deleting_extra_peer_files_in_same_revision(self):STRING
LOW⚡tests/test_hf_cache_management.py637 def test_backup_delete_rechecks_after_remote_ownership_preparation(self):STRING
LOW⚡tests/test_hf_cache_management.py644 def test_backup_delete_refuses_repositories_omitted_by_hf_scan(self):STRING
LOW⚡tests/test_hf_cache_management.py651 def test_existing_backup_and_unsafe_paths_are_preserved(self):STRING
LOW⚡tests/test_hf_cache_management.py660 def test_broken_backup_and_unsafe_restore_symlink_fail(self):STRING
LOW⚡tests/test_hf_cache_management.py670 def test_restore_copy_failure_returns_failure(self):STRING
LOW⚡tests/test_hf_cache_management.py676 def test_invalid_flags_fail_before_cluster_or_cache_access(self):STRING
LOW⚡tests/test_hf_cache_management.py685 def test_invalid_revision_flags_fail_before_cache_access(self):STRING
LOWtests/test_hf_cache_management.py218 def test_portable_backup_delete_list_restore_and_distribute(self):STRING
LOWtests/test_hf_cache_management.py246 def test_portable_backup_selected_revision_only(self):STRING
215 more matches not shown…
Decorative Section Separators30 hits · 93 pts
SeverityFileLineSnippetContext
MEDIUMbuild-and-copy.sh1160# =====================================================COMMENT
MEDIUMbuild-and-copy.sh1162# =====================================================COMMENT
MEDIUMbuild-and-copy.sh1207 # ----------------------------------------------------------COMMENT
MEDIUMbuild-and-copy.sh1209 # ----------------------------------------------------------COMMENT
MEDIUMbuild-and-copy.sh1293 # ----------------------------------------------------------COMMENT
MEDIUMbuild-and-copy.sh1295 # ----------------------------------------------------------COMMENT
MEDIUMbuild-and-copy.sh1408 # ----------------------------------------------------------COMMENT
MEDIUMbuild-and-copy.sh1410 # ----------------------------------------------------------COMMENT
MEDIUMbuild-and-copy.sh1445# =====================================================COMMENT
MEDIUMbuild-and-copy.sh1447# =====================================================COMMENT
MEDIUMtests/test_recipes.sh678# ==============================================================================COMMENT
MEDIUMtests/test_recipes.sh680# ==============================================================================COMMENT
MEDIUMtests/test_recipes.sh1135# ==============================================================================COMMENT
MEDIUMtests/test_recipes.sh1137# ==============================================================================COMMENT
MEDIUMtests/test_recipes.sh1359# ==============================================================================COMMENT
MEDIUMtests/test_recipes.sh1362# ==============================================================================COMMENT
MEDIUM⚡tests/expected_commands.sh10# ==============================================================================COMMENT
MEDIUM⚡tests/expected_commands.sh13# ==============================================================================COMMENT
MEDIUMtests/expected_commands.sh30# ==============================================================================COMMENT
MEDIUMtests/expected_commands.sh33# ==============================================================================COMMENT
MEDIUMtests/expected_commands.sh53# ==============================================================================COMMENT
MEDIUMtests/expected_commands.sh56# ==============================================================================COMMENT
MEDIUMtests/expected_commands.sh70# ==============================================================================COMMENT
MEDIUMtests/expected_commands.sh74# ==============================================================================COMMENT
MEDIUMmods/exp-b12x/run.sh28# ---------------------------------------------------------------COMMENT
MEDIUMmods/exp-b12x/run.sh31# ---------------------------------------------------------------COMMENT
MEDIUMmods/exp-b12x/run.sh50# ---------------------------------------------------------------COMMENT
MEDIUMmods/exp-b12x/run.sh53# ---------------------------------------------------------------COMMENT
MEDIUMmods/exp-b12x/run.sh90# ---------------------------------------------------------------COMMENT
MEDIUMmods/exp-b12x/run.sh97# ---------------------------------------------------------------COMMENT
Excessive Try-Catch Wrapping28 hits · 41 pts
SeverityFileLineSnippetContext
LOWbuild-and-copy.sh298except Exception:CODE
MEDIUMrun-recipe.py101 print("Error: PyYAML is required. Install with: pip install pyyaml")CODE
MEDIUMrun-recipe.py225 print(f"Error: Recipe not found: {recipe_path}")CODE
MEDIUMrun-recipe.py236 print(f"Error: Recipe missing required field: {field}")CODE
MEDIUMrun-recipe.py386 print(f"Error: Build script not found: {BUILD_SCRIPT}")CODE
MEDIUMrun-recipe.py430 print(f"Error: Download script not found: {DOWNLOAD_SCRIPT}")CODE
MEDIUMrun-recipe.py549 print(f"Error: Missing parameter in recipe command: {e}")CODE
MEDIUMrun-recipe.py657 print(f"Error: Autodiscover script not found: {AUTODISCOVER_SCRIPT}")CODE
LOWrun-recipe.py313 except Exception as e:CODE
MEDIUMrun-recipe.py680 print("Error: Autodiscover failed")STRING
MEDIUMrun-recipe.py1144 print(f"Error: Recipe '{recipe['name']}' requires cluster mode.")STRING
MEDIUMrun-recipe.py1155 print(f"Error: Recipe '{recipe['name']}' requires solo mode.")STRING
MEDIUMrun-recipe.py1171 print("Error: --earlyoom requires launch-cluster.sh to clear the image entrypoint.")STRING
MEDIUMrun-recipe.py1240 print(f"Error: {exc}")STRING
MEDIUMrun-recipe.py1262 print("Error: Failed to build container")STRING
MEDIUMrun-recipe.py1270 print("Error: Failed to synchronize container image")STRING
MEDIUMrun-recipe.py1283 print("Error: Failed to build/copy container")STRING
MEDIUMrun-recipe.py1308 print("Error: Failed to download model")STRING
MEDIUMrun-recipe.py1334 print("Error: Failed to build image")STRING
MEDIUM⚡launch-cluster.sh300 print(f'Error: Invalid syntax at line {line_num}: missing \"=\"')CODE
MEDIUM⚡launch-cluster.sh307 print(f'Error: Invalid key format at line {line_num}: {key}')CODE
MEDIUM⚡launch-cluster.sh312 print(f'Error: Duplicate key at line {line_num}: {key}')CODE
MEDIUMcluster_topology.py312 print(f"Error: {exc}", file=sys.stderr)STRING
MEDIUMdocker/validate_flashinfer_wheels.py123 print(f"Error: {exc}.", file=sys.stderr)CODE
LOWmods/fix-qwen3-coder-next/_triton_alloc_setup.py8except Exception:CODE
LOWmods/memory-profile/probe.py137 except Exception as error:CODE
MEDIUMmods/memory-profile/probe.py92def process_start(pid):CODE
LOWmods/inkling-sm12-paged-kv/run.sh58except Exception as exc:CODE
Deep Nesting33 hits · 30 pts
SeverityFileLineSnippetContext
LOWrun-recipe.py613CODE
LOWrun-recipe.py692CODE
LOWhf-cache.py171CODE
LOWhf-cache.py287CODE
LOWhf-cache.py329CODE
LOWcluster_topology.py165CODE
LOWcluster_topology.py222CODE
LOWcluster_topology.py254CODE
LOWcluster_topology.py137CODE
LOWdocker/patch_vllm_spark_kv_cache_cleanup.py69CODE
LOWdocker/patch_vllm_b12x_c128a_topk_alignment.py39CODE
LOWtests/test_instanttensor_vllm_memory_patch.py266CODE
LOWtests/test_cluster_topology.py116CODE
LOWtests/test_cluster_topology.py238CODE
LOWtests/test_launch_cluster_networking.py105CODE
LOWtests/test_launch_cluster_networking.py170CODE
LOWtests/test_memory_capacity.py180CODE
LOWtests/test_memory_capacity.py191CODE
LOWtests/test_memory_capacity.py289CODE
LOWtests/test_hf_download_permissions.py161CODE
LOWtests/test_vllm_api_key_auth_patch.py144CODE
LOWtests/test_vllm_api_key_auth_patch.py166CODE
LOWmods/instanttensor-zero-copy/patch_weight_utils.py121CODE
LOWmods/memory-profile/collect.py17CODE
LOWmods/memory-profile/collect.py36CODE
LOWmods/memory-profile/capacity.py330CODE
LOWmods/memory-profile/capacity.py583CODE
LOWmods/memory-profile/probe.py281CODE
LOWmods/memory-profile/probe.py379CODE
LOWmods/memory-profile/probe.py294CODE
LOWmods/memory-profile/probe.py297CODE
LOWmods/memory-profile/report.py153CODE
LOWmods/memory-profile/report.py272CODE
Redundant / Tautological Comments14 hits · 21 pts
SeverityFileLineSnippetContext
LOWrun-recipe.py1124 # Check if recipe requires cluster modeSTRING
LOWrun-recipe.py1323 # Check if image exists (if not using --setup)STRING
LOWlaunch-cluster.sh385 # Check if non-privileged flags were used without --non-privilegedCOMMENT
LOW⚡launch-cluster.sh479 # Check if it's an absolute path or relative path that existsCOMMENT
LOW⚡launch-cluster.sh482 # Check if it's just a filename, look in examples/ directoryCOMMENT
LOW⚡launch-cluster.sh485 # Check if it's a name without .sh extensionCOMMENT
LOWlaunch-cluster.sh499 # Set command to run the copied script (use absolute path since docker exec may not be in /workspace)COMMENT
LOWlaunch-cluster.sh797# Check if cluster is already runningCOMMENT
LOWlaunch-cluster.sh1657 # Check if ray is responsiveCOMMENT
LOWautodiscover.sh213 # Set IB_IF to all four RoCE interfaces (hardcoded for mesh)COMMENT
LOWautodiscover.sh292 # Check if remote is a GB10 systemCOMMENT
LOWtests/test_recipes.sh1194 # Check if value is present (might be on next line due to formatting)COMMENT
LOWmods/fix-glm-4.7-flash-AWQ/run.sh7# Check if PR 34695 is already applied by looking for the changed fileCOMMENT
LOWmods/fix-glm-4.7-flash-AWQ/run.sh9 # Check if the specific line from PR 34695 is already presentCOMMENT
Empty Error Handlers4 hits · 20 pts
SeverityFileLineSnippetContext
HIGHrun-recipe.py1581except OSError:CODE
HIGHmods/fix-qwen3-coder-next/_triton_alloc_setup.py8except Exception:CODE
HIGHmods/memory-profile/probe.py69except (OSError, ValueError):CODE
HIGHmods/memory-profile/probe.py385except (OSError, ValueError):CODE
Unused Imports19 hits · 18 pts
SeverityFileLineSnippetContext
LOWcluster_topology.py8CODE
LOWdocker/patch_vllm_flashinfer_b12x_swigluoai.py12CODE
LOWdocker/patch_vllm_b12x_c128a_topk_alignment.py10CODE
LOWdocker/patch_vllm_swa_block_size.py4CODE
LOWdocker/patch_vllm_mrv2_speculator_cudagraph_pool.py4CODE
LOWdocker/pin_cutlass_dsl.py8CODE
LOWtests/test_memory_capacity.py4CODE
LOWmods/instanttensor-zero-copy/patch_weight_utils.py4CODE
LOWmods/fix-qwen35-tp4-marlin/fix_rope.py2CODE
LOW…nstanttensor-hybrid-draft-loader/patch_model_loader.py4CODE
LOWmods/memory-profile/patch.py3CODE
LOWmods/memory-profile/collect.py3CODE
LOWmods/memory-profile/capacity.py3CODE
LOWmods/memory-profile/probe.py6CODE
LOWmods/memory-profile/profile_card.py3CODE
LOWmods/memory-profile/report.py3CODE
LOWmods/fix-qwen3-next-autoround/patch_qwen3_next.py4CODE
LOWmods/inkling-sm12-paged-kv/patch_inkling.py4CODE
LOWmods/inkling-sm12-paged-kv/adapter.py9CODE
Self-Referential Comments5 hits · 16 pts
SeverityFileLineSnippetContext
MEDIUMtests/test_recipes.sh532 # Create a temporary recipe with unsupported versionCOMMENT
MEDIUMtests/test_recipes.sh556 # Create a temporary recipe without recipe_versionCOMMENT
MEDIUMtests/test_recipes.sh579 # Create a temporary cluster_only recipeCOMMENT
MEDIUMtests/test_recipes.sh606 # Create a temporary solo_only recipeCOMMENT
MEDIUM⚡tests/expected_commands.sh2# This file is used by test_recipes.sh to verify recipes match README documentationCOMMENT
Docstring Block Structure3 hits · 15 pts
SeverityFileLineSnippetContext
HIGHrun-recipe.py173 Load and validate a recipe YAML file. This function handles recipe resolution from multiple locations and valiSTRING
HIGHrun-recipe.py360 Build the container image using build-and-copy.sh. Delegates to the build-and-copy.sh script which handles mulSTRING
HIGHrun-recipe.py484 Generate a bash launch script from the recipe. Creates a self-contained bash script that runs inside the contaSTRING
Modern AI Meta-Vocabulary2 hits · 6 pts
SeverityFileLineSnippetContext
MEDIUMmods/fix-eagle-fine-prefix/README.md188### RAG, few-shot, and batch evaluationCOMMENT
MEDIUMmods/fix-eagle-fine-prefix/README.md188### RAG, few-shot, and batch evaluationCOMMENT
Over-Commented Block3 hits · 3 pts
SeverityFileLineSnippetContext
LOWtests/test_recipes.sh1#!/bin/bashCOMMENT
LOWtests/expected_commands.sh1# Expected vLLM serve arguments for each recipeCOMMENT
LOWrecipes/glm-4.7-flash-awq.yaml1# Recipe: GLM-4.7-Flash-AWQ-4bitCOMMENT
Example Usage Blocks1 hit · 2 pts
SeverityFileLineSnippetContext
LOWtests/test_recipes.sh8# Usage:COMMENT
Modern Structural Boilerplate1 hit · 1 pts
SeverityFileLineSnippetContext
LOWtests/test_vllm_flashinfer_b12x_patch.py30__all__ = [CODE
AI Structural Patterns1 hit · 1 pts
SeverityFileLineSnippetContext
LOWmods/inkling-sm12-paged-kv/adapter.py19CODE