Agent skill

Fla Nvidia Performance

by fla-org in fla-org/flash-linear-attention

Guidelines for NVIDIA GPU kernel / Triton / Gluon / TileLang / CUDA backend performance work in the FLA repo.

MITAuto-check passedAI & LLM Engineering

Install Fla Nvidia Performance

skills CLI

$ npx skills add fla-org/flash-linear-attention --skill fla-nvidia-performance -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install fla-org/flash-linear-attention fla-nvidia-performance --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/fla-org/flash-linear-attention.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/fla-nvidia-performance .claude/skills/fla-nvidia-performance && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "fla-nvidia-performance" agent skill from https://github.com/fla-org/flash-linear-attention/tree/main/.agents/skills/fla-nvidia-performance into .claude/skills/fla-nvidia-performance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fla-nvidia-performance", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/fla-org/flash-linear-attention/tree/main/.agents/skills/fla-nvidia-performance

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add fla-org/flash-linear-attention --skill fla-nvidia-performance -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install fla-org/flash-linear-attention fla-nvidia-performance --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/fla-org/flash-linear-attention.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/fla-nvidia-performance .agents/skills/fla-nvidia-performance && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "fla-nvidia-performance" agent skill from https://github.com/fla-org/flash-linear-attention/tree/main/.agents/skills/fla-nvidia-performance into .agents/skills/fla-nvidia-performance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fla-nvidia-performance", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add fla-org/flash-linear-attention --skill fla-nvidia-performance -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install fla-org/flash-linear-attention fla-nvidia-performance --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/fla-org/flash-linear-attention.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/fla-nvidia-performance .cursor/skills/fla-nvidia-performance && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "fla-nvidia-performance" agent skill from https://github.com/fla-org/flash-linear-attention/tree/main/.agents/skills/fla-nvidia-performance into .cursor/skills/fla-nvidia-performance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fla-nvidia-performance", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/fla-org/flash-linear-attention.git --path .agents/skills/fla-nvidia-performance

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add fla-org/flash-linear-attention --skill fla-nvidia-performance -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install fla-org/flash-linear-attention fla-nvidia-performance --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/fla-org/flash-linear-attention.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/fla-nvidia-performance .gemini/skills/fla-nvidia-performance && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "fla-nvidia-performance" agent skill from https://github.com/fla-org/flash-linear-attention/tree/main/.agents/skills/fla-nvidia-performance into .gemini/skills/fla-nvidia-performance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fla-nvidia-performance", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install fla-org/flash-linear-attention fla-nvidia-performance

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add fla-org/flash-linear-attention --skill fla-nvidia-performance -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/fla-org/flash-linear-attention.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/fla-nvidia-performance .github/skills/fla-nvidia-performance && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "fla-nvidia-performance" agent skill from https://github.com/fla-org/flash-linear-attention/tree/main/.agents/skills/fla-nvidia-performance into .github/skills/fla-nvidia-performance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fla-nvidia-performance", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add fla-org/flash-linear-attention --skill fla-nvidia-performance -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install fla-org/flash-linear-attention fla-nvidia-performance --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/fla-org/flash-linear-attention.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/fla-nvidia-performance .opencode/skills/fla-nvidia-performance && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "fla-nvidia-performance" agent skill from https://github.com/fla-org/flash-linear-attention/tree/main/.agents/skills/fla-nvidia-performance into .opencode/skills/fla-nvidia-performance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fla-nvidia-performance", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: fla-nvidia-performance
GitHub stars: 5.8k
Token cost: ~1.2k tokens
SKILL.md length: 445 words
Files: 1
Skills in repo: 9
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Guidelines for NVIDIA GPU kernel / Triton / Gluon / TileLang / CUDA backend performance work in the FLA repo.

Works in 4 steps: Before / after benchmark → Profiling when needed → Workload coverage → …
AI & LLM Engineering work in your project
SKILL.md covers Hardware baseline, Detailed NCU workflow, Day-to-day development and Before opening a PR…, plus 2 more sections
Calls python

What it does

Fla Nvidia Performance is an agent skill from fla-org/flash-linear-attention. Guidelines for NVIDIA GPU kernel / Triton / Gluon / TileLang / CUDA backend performance work in the FLA repo. Covers profiling workflow, hardware baselines, and PR-ready performance evidence requirements. Uses an installed ncu-report-skill when a task needs detailed Nsight Compute collection and diagnosis.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering. It works with NVIDIA AI Platform and CUDA. The repository describes itself as: 🚀 Efficient implementations for emerging model architectures. The licence is MIT.

When your agent uses it

AI & LLM Engineering work in your project

Example prompts

“Use the fla-nvidia-performance skill to guideline for NVIDIA GPU kernel / Triton / Gluon / TileLang / CUDA backend performance work in the FLA repo”
“/fla-nvidia-performance”

Requirements

Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

Before / after benchmark
Profiling when needed
Workload coverage
Conclusion and risk

What it can do on your machine

Read from SKILL.md and the folder at commit 72ac946. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Fla Nvidia Performance loads about 1.2k tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 445 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~83
When it runs · the whole SKILL.md, loaded when a task matches: ~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from fla-org/flash-linear-attention at commit 72ac946, republished under its MIT licence (© fla-org). 445 words, ~1,155 tokens.

Download SKILL.mdSave it as .claude/skills/fla-nvidia-performance/SKILL.md (or your agent's skills folder).

name: fla-nvidia-performance
description: Guidelines for NVIDIA GPU kernel / Triton / Gluon / TileLang / CUDA backend performance work in the FLA repo. Covers profiling workflow, hardware baselines, and PR-ready performance evidence requirements. Uses an installed ncu-report-skill when a task needs detailed Nsight Compute collection and diagnosis.

FLA NVIDIA Performance Skill

Use this skill when working on Triton, Gluon, TileLang, CUDA, or other NVIDIA GPU kernel optimizations, backend tuning, or any change that could affect throughput or latency in fla/ops/ or related modules.

Hardware baseline

Minimum effective baseline: datacenter NVIDIA GPUs with sm_90 or newer; H100 / H20 are accepted.
Preferred targets: datacenter NVIDIA GPUs with sm_100 or sm_103.
Reference only: A100 (sm_80), pre-sm_80 GPUs, and all consumer cards (including sm_86, sm_89, and sm_120). Do not use these numbers as the only PR performance conclusion.

Detailed NCU workflow

This repo intentionally does not vendor ncu-report-skill, add it as a submodule, or auto-clone it during agent work.

If a user-level ncu-report-skill is available, use it for:

Nsight Compute collection details (full, source, PM sampling, source counters);
sm_100 / sm_103 metric-name caveats;
report parsing helpers and diagnosis playbooks;
the final profiling report structure.

If it is not available, use the minimal NCU commands in this skill. Report any missing profiling evidence and its technical limitation; the availability of a helper skill does not belong in the PR description. Do not create untracked external clones inside this repo unless the user explicitly asks.

Day-to-day development

You are not required to run NCU for every incremental change.
Quick sanity checks with benchmark_training_throughput.py or benchmark_generation.py are enough to catch large regressions during development.
Prefer dense workloads for quick iteration; varlen workloads are checked before PR.

Show full SKILL.md (214 more words)Show less

Before opening a PR (performance evidence)

For NVIDIA performance-optimization PRs, collect the evidence below. Correctness-only kernel changes still need the tests and same-hardware benchmarks required by CONTRIBUTING.md; detailed profiling is needed when it explains a performance claim or unresolved regression.

Before / after benchmark
- Run the same benchmark script with the same workload on the same hardware.
- Report throughput (tokens/s or iters/s) and, if relevant, peak memory.
Profiling when needed
- Use NCU when explaining a bottleneck, performance claim, or unresolved regression needs hardware metrics. It is not a mandatory check for every PR.
- When collecting NCU evidence, run ncu with --set full and --set source for a representative changed kernel when Nsight Compute is available.
- Capture the .ncu-rep locally; do not commit it to the repo.
- In the PR description, paste a short summary of key metrics (e.g., memory throughput %, SOL, occupancy, top hot instructions).
Workload coverage
- Include at least one dense workload.
- Include at least one variable-length workload if the op supports it.
Conclusion and risk
- State whether the change is an improvement, neutral, or a known trade-off.
- Flag any backend or shape that regressed and explain why.

Profile artifact layout

Store local profile artifacts under:

text

profile/<run_name>/

For example:

text

profile/kda_chunk_bwd_20250603/
  ├── REPORT.md
  ├── reports/
  │   ├── full_<tag>.ncu-rep
  │   └── source_<tag>.ncu-rep
  └── analysis/

Keep .ncu-rep, .nsys-rep, and raw logs out of git.

Quick commands reference

bash

# Op microbenchmark
python -m benchmarks.ops.run --op chunk_kda --modes fwd

# Model training benchmark
python benchmarks/benchmark_training_throughput.py \
  --name kda --batch_size 2 --seq_len 8192

# Varlen training benchmark (if supported by the model/op path)
python benchmarks/benchmark_training_throughput.py \
  --name kda --batch_size 2 --seq_len 8192 --varlen

# NCU full profile
ncu --set full --section PmSampling --section PmSampling_WarpStates \
  -k "regex:<kernel_regex>" -c 1 \
  -o profile/<run_name>/reports/full_<tag> \
  python -m benchmarks.ops.run --op chunk_kda --modes fwd

# NCU source profile (for instruction-level analysis)
ncu --set source --section SourceCounters \
  -k "regex:<kernel_regex>" -c 1 \
  -o profile/<run_name>/reports/source_<tag> \
  python -m benchmarks.ops.run --op chunk_kda --modes fwd

Files

Just SKILL.md in .agents/skills/fla-nvidia-performance of fla-org/flash-linear-attention.

Open the folder on GitHubat commit 72ac946

Compare with similar skills

Fla Nvidia Performance next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Fla Nvidia Performance compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Fla Nvidia Performance this skillfla-org/flash-linear-attention	5.8k	—	~1.2k	Automated safety check: Pass	MIT	today
Graphsignalgraphsignal/graphsignal	257	—	~6.2k	Automated safety check: Pass	Apache-2.0	10 days ago
LLM Torch Profiler Trace AnalysisBBuf/AI-Infra-Auto-Driven-SKILLS	911	—	~2.8k	Automated safety check: Pass	None	3 days ago
Optimize OpCVCUDA/CV-CUDA	2.7k	—	~834	Automated safety check: Pass	Custom licence	21 days ago
Cutlass SkillslowlyC/agent-gpu-skills	169	—	~1.3k	Automated safety check: Pass	MIT	2 mo ago
Setup Workshop Nemoclawbrevdev/workshop-build-an-agent	144	—	~5.2k	Automated safety check: Pass	Apache-2.0	yesterday

Similar skills

Graphsignal
graphsignal/graphsignal
Profile AI inference workloads (vLLM, SGLang, TensorRT-LLM, PyTorch, any GPU application) with the Graphsignal profiler and read the results from its local /signals JSON endpoint.
257 GitHub stars~6.2k tokensUpdated 10 days ago
AI & LLM EngineeringAuto-check passed
LLM Torch Profiler Trace Analysis
BBuf/AI-Infra-Auto-Driven-SKILLS
Analyzes Torch Profiler traces from SGLang, vLLM and TensorRT-LLM servers into kernel attribution, overlap and fusion tables.
911 GitHub stars~2.8k tokensUpdated 3 days ago
AI & LLM EngineeringAuto-check passed
Optimize Op
CVCUDA/CV-CUDA
Drive a single-operator optimization campaign per .agents/guidance/OPTIMIZATIONGUIDELINES.md, with a deterministically enforced definition-of-done and versioned MR summary.
2.7k GitHub stars~834 tokensUpdated 21 days ago
AI & LLM EngineeringAuto-check passed
Cutlass Skill
slowlyC/agent-gpu-skills
Write, debug, and optimize CUTLASS, CuTe, and CuTeDSL GPU kernels from local upstream source, examples, and headers.
169 GitHub stars~1.3k tokensUpdated 2 mo ago
AI & LLM EngineeringAuto-check passed
Setup Workshop Nemoclaw
brevdev/workshop-build-an-agent
Set up the NVIDIA "Build an Agent" DevX workshop as a working JupyterLab environment from INSIDE a locked-down OpenShell/NemoClaw sandbox, and hand the user the token URL + access commands.
144 GitHub stars~5.2k tokensUpdated yesterday
AI & LLM EngineeringAuto-check passed
Cv Deploy
LMIXR/CV_Deployment_skill
基于 helpfile 工程经验，协助 agent 配置 CV 主机和边缘设备环境、编译视觉与推理依赖、接入摄像头视频并打包部署服务。适用于 Ubuntu、CentOS、Windows、macOS、Jetson、树莓派和 RK3399 的 CV 工程实施与故障排查，以及相关移动端配套工具；模型训练和纯算法设计不属于本技能主线。
146 GitHub stars~547 tokensUpdated 9 days ago
AI & LLM EngineeringAuto-check passed

More from fla-org/flash-linear-attention

All 9 skills in this repo

Fla Ascend Performance
fla-org/flash-linear-attention
Guidelines for Ascend NPU kernel / Triton-Ascend backend performance work in the FLA repo.
5.8k GitHub stars~6.3k tokensUpdated today
Auto-check passed
Fla Optimization Loop
fla-org/flash-linear-attention
Disciplined, reproducible loop for making an FLA kernel faster (Triton, Gluon, TileLang, CuTe) without ever breaking or gaming correctness.
5.8k GitHub stars~3.1k tokensUpdated today
Auto-check passed
Fla Triton To Gluon
fla-org/flash-linear-attention
Workflow for porting an existing Triton kernel in fla/ops/ to Gluon (triton.experimental.gluon) to gain explicit control over tensor layouts, shared memory, async data movement (cp.async / TMA), MMA…
5.8k GitHub stars~4.2k tokensUpdated today
Auto-check passed
Fla Correctness Coverage
fla-org/flash-linear-attention
Guidelines for kernel correctness testing and coverage in fla/ops/ and related modules, including common Triton grid/addressing pitfalls.
5.8k GitHub stars~1.5k tokensUpdated today
Auto-check passed
Fla Design Coverage
fla-org/flash-linear-attention
Contract-first design and coverage discipline for FLA kernel and numerical changes.
5.8k GitHub stars~3.6k tokensUpdated today
Auto-check passed
Fla Dispatch Backends
fla-org/flash-linear-attention
Workflow for FLA backend dispatch decorators and backend implementations.
5.8k GitHub stars~1.1k tokensUpdated today
Auto-check passed

Works with

Questions about Fla Nvidia Performance

What does Fla Nvidia Performance do?

Guidelines for NVIDIA GPU kernel / Triton / Gluon / TileLang / CUDA backend performance work in the FLA repo. Fla Nvidia Performance is an agent skill from fla-org/flash-linear-attention. Guidelines for NVIDIA GPU kernel / Triton / Gluon / TileLang / CUDA backend performance work in the FLA repo.

When should I use Fla Nvidia Performance?

Fla Nvidia Performance fits situations like: AI & LLM Engineering work in your project.

How do I install Fla Nvidia Performance in Claude Code?

Run `npx skills add fla-org/flash-linear-attention --skill fla-nvidia-performance -a claude-code`. Or copy the skill folder (.agents/skills/fla-nvidia-performance in fla-org/flash-linear-attention) into .claude/skills/fla-nvidia-performance in your project. Claude Code loads it when a task matches its description.

How do I install Fla Nvidia Performance in Codex?

Run `npx skills add fla-org/flash-linear-attention --skill fla-nvidia-performance -a codex`. Or copy the skill folder (.agents/skills/fla-nvidia-performance in fla-org/flash-linear-attention) into .agents/skills/fla-nvidia-performance in your project. Codex loads it when a task matches its description.

Can I use Fla Nvidia Performance in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add fla-org/flash-linear-attention --skill fla-nvidia-performance -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fla-nvidia-performance, .gemini/skills/fla-nvidia-performance, .github/skills/fla-nvidia-performance and .opencode/skills/fla-nvidia-performance in your project.

What does Fla Nvidia Performance need to run?

Going by SKILL.md and its folder, Fla Nvidia Performance needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Fla Nvidia Performance access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Fla Nvidia Performance safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Fla Nvidia Performance use?

Fla Nvidia Performance is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Fla Nvidia Performance use?

About 1.2k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Fla Nvidia Performance?

Skills that share tags, products or a category with Fla Nvidia Performance: Graphsignal (graphsignal/graphsignal, 257 stars), LLM Torch Profiler Trace Analysis (BBuf/AI-Infra-Auto-Driven-SKILLS, 911 stars), Optimize Op (CVCUDA/CV-CUDA, 2.7k stars) and Cutlass Skill (slowlyC/agent-gpu-skills, 169 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fla Nvidia Performance?

fla-org (a GitHub organization) maintains it in fla-org/flash-linear-attention, which has 5,831 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 8, 2026.

Source: fla-org/flash-linear-attention on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Fla Nvidia Performance

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

FLA NVIDIA Performance Skill

Hardware baseline

Detailed NCU workflow

Day-to-day development

Before opening a PR (performance evidence)

Profile artifact layout

Quick commands reference

Files

Compare with similar skills

Similar skills

More from fla-org/flash-linear-attention

Related

Questions about Fla Nvidia Performance