Skip to main content
Glama
Sign In
hotkernel

hotkernel

by xinhuagu
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to hotkernel

No user-submitted related servers found.

    Related Servers

    • Flameox

      Deboer6105
      F
      license
      Not graded
      quality
      A
      maintenance
      Enables coding agents to trace, profile, and investigate performance hotspots in application code, native code, GPU kernels, and inference stacks by coordinating local profilers, benchmark tools, trace processors, and direct capture targets. Returns bounded, typed runtime evidence with observed inputs, provenance, coverage, and limitations, all through explicit artifact paths or commands with no workspace setup required.
      -

    • io.github.morluto/flameox

      debram03144
      F
      license
      Not graded
      quality
      A
      maintenance
      Enables coding agents to coordinate local profilers, benchmark tools, trace processors, and direct targets, turning explicit artifacts or commands into bounded runtime evidence with provenance, coverage, and limitations. It exposes analysis and capture tools that help trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks without workspace setup or a hosted service.
      -

    • io.github.morluto/flameox

      BrianDabrowski64376
      F
      license
      Not graded
      quality
      A
      maintenance
      Enables coding agents to turn explicit artifacts or commands into bounded local runtime evidence from profilers, benchmarks, trace processors, and direct targets, with typed provenance, coverage, and optional durable preservation. It exposes analysis and capture tools for tracing, profiling, and investigating hotspots in application and native code, GPU kernels, and inference stacks.
      -

    • io.github.morluto/flameox

      RafaelKim063
      F
      license
      Not graded
      quality
      A
      maintenance
      Enables coding agents to run bounded local profiling, benchmarking, tracing, and capture workflows against explicit artifacts or commands, returning typed evidence, provenance, coverage, and limitations for investigating application, native, GPU, and inference hotspots.
      -

    • flameox

      alessandrop90409
      F
      license
      Not graded
      quality
      A
      maintenance
      Enables coding agents to run profilers, benchmark tools, and trace processors against explicit artifact paths or local commands, returning bounded, typed runtime evidence with coverage and provenance for tracing and profiling hotspots in application code, native code, GPU kernels, and inference stacks. Analysis and capture tools also support optional durable evidence preservation and inline replay of stored results.
      -
    Deploy Server
    Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

    TDQS

    A3.8/5.0

    Scored across 10 tools

    Disambiguation4/5

    Each tool occupies a distinct step in the optimize-measure-record loop, and descriptions explicitly order them (torch_trace 'use this first', profile for nsys/ncu, top_kernels for saved CSVs). The only real overlap is torch_trace vs profile vs top_kernels, all producing kernel-time breakdowns, though the backend/input distinction is spelled out. gpu_info returning a roofline entry also slightly blurs with roofline, but the primary purposes remain clear.

    Naming Consistency4/5

    All names are lowercase snake_case with no style mixing. There is a mild convention split between noun-style query tools (gpu_info, roofline, top_kernels) and verb-style action tools (bench, verify, record, disasm, profile, new_target), but this reads naturally and predictably.

    Tool Count5/5

    Ten tools map cleanly onto the kernel-speedrun pipeline: environment info, scaffolding, tracing, profiling, analysis, benchmarking, verification, and recording. Nothing feels redundant or missing at the count level.

    Completeness4/5

    The surface covers the full lifecycle from scaffolding a target (new_target) through measurement (bench/verify/profile) to persistent, reproducible logging (record regenerating LEADERBOARD.md). Minor gaps: no tool to list existing targets/results or inspect history without regenerating the leaderboard, and no way to remove or invalidate a bad record.

    Maintenance

    ActivityMaintained
    ResponsivenessSyncing

    Resources