[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A9HDRE6PDF4PPKEJ4MJCZW":3,"skill-same:01M7A9HDRE6PDF4PPKEJ4MJCZW":73},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7A9HDRE6PDF4PPKEJ4MJCZW","nemo-mbridge-perf-activation-recompute",null,"Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute.","themusebook\u002Fskills","themusebook","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F349927247?v=4","01M7A5C1RV5S3V5FF6ZACVDNRN","musebook","01M7A5C1SFC3KRZAXNN60XJ7KM",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-mbridge-perf-activation-recompute\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: nemo-mbridge-perf-activation-recompute\ndescription: Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute.\nlicense: Apache-2.0\nwhen_to_use: Reducing GPU memory via activation recompute, or investigating a commit that changed recompute settings and caused OOM or a regression; 'recompute_granularity', 'recompute_num_layers', 'recompute_modules', 'recompute_method', 'selective recompute', 'full recompute', 'activation memory OOM'.\n---\n\n# Activation Recompute\n\nStable docs: @docs\u002Ftraining\u002Factivation-recomputation.md\nCard: @skills\u002Fnemo-mbridge-perf-activation-recompute\u002Fcard.yaml\n\n\u003C!-- NVSkills CI refresh: 2026-06-15. No instruction changes. -->\n\n## What It Is\n\nActivation recompute trades GPU compute for memory by discarding intermediate\nactivations during the forward pass and recomputing them during backward.\nMegatron Bridge supports two granularities:\n\n| Granularity | What you specify | What gets recomputed | Memory savings | Compute cost |\n|---|---|---|---|---|\n| `selective` | `recompute_modules` list (e.g. `core_attn`, `mlp`) | specific submodules within each layer | moderate (module-dependent) | low to high |\n| `full` | `recompute_num_layers` + `recompute_method` | entire transformer layers (N layers) | strongest | highest |\n\nNote: MCore names these \"selective\" (submodule-level) vs \"full\" (layer-level).\n\"Full\" means recomputing full layers, not the full model — you still choose\nhow many layers via `recompute_num_layers`.\n\n## Quick Decision\n\n1. Rule out allocator fragmentation first with\n   `PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True`; see\n   @skills\u002Fnemo-mbridge-perf-memory-tuning\u002FSKILL.md.\n2. For activation pressure, start with selective recompute:\n   `recompute_granularity=\"selective\"` and `recompute_modules=[\"core_attn\"]`.\n3. Add modules by cost: `\"layernorm\"` is cheap but saves little, while `\"mlp\"`\n   saves much more memory at a clear throughput cost.\n4. Use full-layer recompute only when selective recompute does not fit, and set\n   all required fields: `recompute_granularity=\"full\"`, `recompute_method`, and\n   `recompute_num_layers`.\n5. With FP8 or TE-scoped CUDA graphs, avoid full-layer recompute unless graph\n   scope is `full_iteration`; otherwise use selective recompute or disable TE\n   graph capture.\n\nCPU offloading (`cpu_offloading=True`) is an alternative that avoids recompute\ncost entirely, but it is **incompatible with PP > 1**.\n\n## Enablement\n\n### Selective recompute\n\n```python\ncfg.model.recompute_granularity = \"selective\"\ncfg.model.recompute_modules = [\"core_attn\"]  # add \"layernorm\", \"mlp\", or other valid modules as needed\n```\n\n### Full-layer recompute\n\n```python\ncfg.model.recompute_granularity = \"full\"\ncfg.model.recompute_method = \"uniform\"\ncfg.model.recompute_num_layers = 4\n```\n\n### Available recompute_modules\n\n| Module | What it recomputes | Compute cost | Memory savings |\n|---|---|---|---|\n| `core_attn` | attention softmax\u002Fdropout\u002FQKV dot product | low (Flash Attention already recomputes internally) | moderate |\n| `layernorm` | layer normalization | negligible (~0%) | negligible |\n| `mlp` | full FFN block | high (~16% on Llama3 70B, hidden=28672) | ~3 GB |\n| `moe` | MoE expert dispatch | varies | varies |\n| `moe_act` | MoE activation functions | low | small |\n| `shared_experts` | shared expert layers | moderate | moderate |\n| `mla_up_proj` | Multi-Latent Attention up projection | moderate | moderate |\n\n### Performance harness CLI\n\n```bash\nuv run python scripts\u002Fperformance\u002Frun_script.py \\\n  -m llama \\\n  -mr llama3_8b \\\n  --task pretrain \\\n  -g h100 \\\n  -c bf16 \\\n  -ng 8 \\\n  --recompute_modules core_attn,layernorm \\\n  ...\n```\n\n## Compatibility and Constraints\n\n- `recompute_granularity=selective` requires a non-empty `recompute_modules` list\n- `recompute_granularity=full` requires `recompute_method` and `recompute_num_layers`\n- **Layer-level recompute (`recompute_granularity=\"full\"` +\n  `recompute_num_layers`) is incompatible with TE-scoped CUDA graphs.**\n  MCore calls this \"full\" granularity — the name refers to recomputing\n  full transformer layers, not the full model. Even though you're selecting\n  how many layers to recompute, MCore treats it differently from submodule\n  recompute. Any TE-scoped scope (`attn`, `mlp`, `moe_router`, etc.) will\n  assert. This commonly hits FP8 configs that enable TE-scoped graphs by\n  default (e.g. `LLAMA3_70B_SFT_CONFIG_H100_FP8_CS_V1` sets\n  `cuda_graph_impl=\"transformer_engine\"`, `cuda_graph_scope=\"mlp\"`). Options:\n  - use submodule recompute (`recompute_granularity=\"selective\"` +\n    `recompute_modules`) — compatible with TE-scoped graphs\n  - disable CUDA graphs (`cuda_graph_impl=\"none\"`) and use layer-level recompute\n  - switch to `cuda_graph_impl=\"local\"`, `cuda_graph_scope=\"full_iteration\"`\n- `distribute_saved_activations=True` cannot be combined with `sequence_parallel=True`\n- Combining `mlp` + `core_attn` recompute is slightly worse than `mlp` alone\n  due to double recompute overhead\n\n## Measured Results\n\nLlama3 70B SFT on 32x H100 80GB, FP8 (Current Scaling):\n- Baseline: TP=4, PP=4, VPP=5, DP=2, MBS=1, GBS=32, seq_len=4096\n- Golden GPU utilization: 709.93 TFLOP\u002Fs\u002FGPU\n- Regression threshold: 5%\n\n| Experiment | recompute_modules | TFLOP\u002Fs\u002FGPU | vs Golden | Peak Mem (GB) | Result |\n|---|---|---|---|---|---|\n| Baseline | [core_attn] | ~704 | -0.8% | 58.8 (OOM rank0) | OOM |\n| Exp 1 | [mlp] | 593.6 | -16.4% | 55.6 | Perf regression |\n| Exp 2 | [mlp, core_attn] | 586.8 | -17.3% | 55.6 | Perf regression |\n| Exp 3 | [core_attn, layernorm] | ~702 | -1.1% | 59.6 (OOM rank0) | OOM |\n\nKey takeaways:\n\n- `layernorm` recompute is nearly free compute-wise but saves negligible memory\n- `mlp` recompute saves ~3 GB peak but costs ~16% because the Llama3 70B FFN\n  (hidden=28672) is expensive to recompute\n- Combining `mlp` + `core_attn` is slightly worse than `mlp` alone\n- For this workload, the actual OOM fix was `PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True`\n  (memory fragmentation, not capacity). See @skills\u002Fnemo-mbridge-perf-memory-tuning\u002FSKILL.md.\n\n## Code Anchors\n\n### Recompute modules enum and selective checkpoint logic\n\n```python\n# 3rdparty\u002FMegatron-LM\u002Fmegatron\u002Fcore\u002Ftransformer\u002Ftransformer_block.py\n# _checkpointed_forward() applies selective recompute based on recompute_modules\n```\n\n### Recompute config validation\n\n```python\n# 3rdparty\u002FMegatron-LM\u002Fmegatron\u002Fcore\u002Ftransformer\u002Ftransformer_config.py\n# Validates recompute_granularity, recompute_method, recompute_num_layers\n```\n\n### Llama3 recipe defaults\n\n```99:103:src\u002Fmegatron\u002Fbridge\u002Frecipes\u002Fllama\u002Fllama3.py\n    # Memory saving (recompute & offloading)\n    cfg.model.recompute_granularity = None\n    cfg.model.recompute_modules = None\n    cfg.model.fine_grained_activation_offloading = False\n    cfg.model.offload_modules = None\n```\n\n### Full recompute + CUDA graph assertion (MCore)\n\n```2001:2005:3rdparty\u002FMegatron-LM\u002Fmegatron\u002Fcore\u002Ftransformer\u002Ftransformer_config.py\n            if self.recompute_granularity:\n                if self.recompute_granularity != \"selective\":\n                    assert self.cuda_graph_scope == [\n                        CudaGraphScope.full_iteration\n                    ], \"full recompute is only supported with full iteration CUDA graph.\"\n```\n\n### CPU offloading PP incompatibility (MCore)\n\n```1303:1306:3rdparty\u002FMegatron-LM\u002Fmegatron\u002Fcore\u002Ftransformer\u002Ftransformer_config.py\n        if self.cpu_offloading and self.pipeline_model_parallel_size > 1:\n            raise ValueError(\n                \"Currently there is no support for Pipeline parallelism with CPU offloading\"\n            )\n```\n\n## Failure Diagnosis\n\n| Symptom | Cause | Confirm | Fix |\n|---|---|---|---|\n| >15% GPU utilization drop | `mlp` recompute on a large FFN | check whether `recompute_modules` includes `mlp` | remove `mlp`, lower micro batch size, or use CPU offload if PP=1 |\n| Still OOM after adding layernorm | layernorm activations are too small to move the peak materially | compare peak memory before\u002Fafter | switch to a higher-impact module or full-layer recompute |\n| `AssertionError: full recompute is only supported with full iteration CUDA graph` | layer-level recompute with TE-scoped graph capture | check `cuda_graph_impl` and `cuda_graph_scope` | use `selective`, set `cuda_graph_impl=none`, or use `local` + `full_iteration` |\n| ValueError: PP + CPU offloading | `cpu_offloading=True` with `pipeline_model_parallel_size > 1` | check PP config | disable CPU offloading or set PP=1 |\n| mlp+core_attn worse than mlp alone | double recompute overhead | compare Exp 1 vs Exp 2 | use mlp alone |\n\n## Known Limitations\n\n- Per-module memory savings vary significantly by model architecture and hidden\n  dimension\n- No automatic module selection — users must choose which modules to recompute\n- `layernorm` recompute is almost never worth it as a standalone fix\n- CPU offloading (the zero-compute-cost alternative) is blocked when PP > 1\n\n## Verification\n\n```bash\nuv run python -m pytest \\\n  tests\u002Funit_tests\u002Ftraining\u002Ftest_config.py -k \"recompute\" -q\n```\n\nSuccess criteria:\n- Unit tests pass for recompute config validation\n- No assertion errors from config validation\n","# Activation Recompute\n\nStable docs: @docs\u002Ftraining\u002Factivation-recomputation.md\nCard: @skills\u002Fnemo-mbridge-perf-activation-recompute\u002Fcard.yaml\n\n\u003C!-- NVSkills CI refresh: 2026-06-15. No instruction changes. -->\n\n## What It Is\n\nActivation recompute trades GPU compute for memory by discarding intermediate\nactivations during the forward pass and recomputing them during backward.\nMegatron Bridge supports two granularities:\n\n| Granularity | What you specify | What gets recomputed | Memory savings | Compute cost |\n|---|---|---|---|---|\n| `selective` | `recompute_modules` list (e.g. `core_attn`, `mlp`) | specific submodules within each layer | moderate (module-dependent) | low to high |\n| `full` | `recompute_num_layers` + `recompute_method` | entire transformer layers (N layers) | strongest | highest |\n\nNote: MCore names these \"selective\" (submodule-level) vs \"full\" (layer-level).\n\"Full\" means recomputing full layers, not the full model — you still choose\nhow many layers via `recompute_num_layers`.\n\n## Quick Decision\n\n1. Rule out allocator fragmentation first with\n   `PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True`; see\n   @skills\u002Fnemo-mbridge-perf-memory-tuning\u002FSKILL.md.\n2. For activation pressure, start with selective recompute:\n   `recompute_granularity=\"selective\"` and `recompute_modules=[\"core_attn\"]`.\n3. Add modules by cost: `\"layernorm\"` is cheap but saves little, while `\"mlp\"`\n   saves much more memory at a clear throughput cost.\n4. Use full-layer recompute only when selective recompute does not fit, and set\n   all required fields: `recompute_granularity=\"full\"`, `recompute_method`, and\n   `recompute_num_layers`.\n5. With FP8 or TE-scoped CUDA graphs, avoid full-layer recompute unless graph\n   scope is `full_iteration`; otherwise use selective recompute or disable TE\n   graph capture.\n\nCPU offloading (`cpu_offloading=True`) is an alternative that avoids recompute\ncost entirely, but it is **incompatible with PP > 1**.\n\n## Enablement\n\n### Selective recompute\n\n```python\ncfg.model.recompute_granularity = \"selective\"\ncfg.model.recompute_modules = [\"core_attn\"]  # add \"layernorm\", \"mlp\", or other valid modules as needed\n```\n\n### Full-layer recompute\n\n```python\ncfg.model.recompute_granularity = \"full\"\ncfg.model.recompute_method = \"uniform\"\ncfg.model.recompute_num_layers = 4\n```\n\n### Available recompute_modules\n\n| Module | What it recomputes | Compute cost | Memory savings |\n|---|---|---|---|\n| `core_attn` | attention softmax\u002Fdropout\u002FQKV dot product | low (Flash Attention already recomputes internally) | moderate |\n| `layernorm` | layer normalization | negligible (~0%) | negligible |\n| `mlp` | full FFN block | high (~16% on Llama3 70B, hidden=28672) | ~3 GB |\n| `moe` | MoE expert dispatch | varies | varies |\n| `moe_act` | MoE activation functions | low | small |\n| `shared_experts` | shared expert layers | moderate | moderate |\n| `mla_up_proj` | Multi-Latent Attention up projection | moderate | moderate |\n\n### Performance harness CLI\n\n```bash\nuv run python scripts\u002Fperformance\u002Frun_script.py \\\n  -m llama \\\n  -mr llama3_8b \\\n  --task pretrain \\\n  -g h100 \\\n  -c bf16 \\\n  -ng 8 \\\n  --recompute_modules core_attn,layernorm \\\n  ...\n```\n\n## Compatibility and Constraints\n\n- `recompute_granularity=selective` requires a non-empty `recompute_modules` list\n- `recompute_granularity=full` requires `recompute_method` and `recompute_num_layers`\n- **Layer-level recompute (`recompute_granularity=\"full\"` +\n  `recompute_num_layers`) is incompatible with TE-scoped CUDA graphs.**\n  MCore calls this \"full\" granularity — the name refers to recomputing\n  full transformer layers, not the full model. Even though you're selecting\n  how many layers to recompute, MCore treats it differently from submodule\n  recompute. Any TE-scoped scope (`attn`, `mlp`, `moe_router`, etc.) will\n  assert. This commonly hits FP8 configs that enable TE-scoped graphs by\n  default (e.g. `LLAMA3_70B_SFT_CONFIG_H100_FP8_CS_V1` sets\n  `cuda_graph_impl=\"transformer_engine\"`, `cuda_graph_scope=\"mlp\"`). Options:\n  - use submodule recompute (`recompute_granularity=\"selective\"` +\n    `recompute_modules`) — compatible with TE-scoped graphs\n  - disable CUDA graphs (`cuda_graph_impl=\"none\"`) and use layer-level recompute\n  - switch to `cuda_graph_impl=\"local\"`, `cuda_graph_scope=\"full_iteration\"`\n- `distribute_saved_activations=True` cannot be combined with `sequence_parallel=True`\n- Combining `mlp` + `core_attn` recompute is slightly worse than `mlp` alone\n  due to double recompute overhead\n\n## Measured Results\n\nLlama3 70B SFT on 32x H100 80GB, FP8 (Current Scaling):\n- Baseline: TP=4, PP=4, VPP=5, DP=2, MBS=1, GBS=32, seq_len=4096\n- Golden GPU utilization: 709.93 TFLOP\u002Fs\u002FGPU\n- Regression threshold: 5%\n\n| Experiment | recompute_modules | TFLOP\u002Fs\u002FGPU | vs Golden | Peak Mem (GB) | Result |\n|---|---|---|---|---|---|\n| Baseline | [core_attn] | ~704 | -0.8% | 58.8 (OOM rank0) | OOM |\n| Exp 1 | [mlp] | 593.6 | -16.4% | 55.6 | Perf regression |\n| Exp 2 | [mlp, core_attn] | 586.8 | -17.3% | 55.6 | Perf regression |\n| Exp 3 | [core_attn, layernorm] | ~702 | -1.1% | 59.6 (OOM rank0) | OOM |\n\nKey takeaways:\n\n- `layernorm` recompute is nearly free compute-wise but saves negligible memory\n- `mlp` recompute saves ~3 GB peak but costs ~16% because the Llama3 70B FFN\n  (hidden=28672) is expensive to recompute\n- Combining `mlp` + `core_attn` is slightly worse than `mlp` alone\n- For this workload, the actual OOM fix was `PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True`\n  (memory fragmentation, not capacity). See @skills\u002Fnemo-mbridge-perf-memory-tuning\u002FSKILL.md.\n\n## Code Anchors\n\n### Recompute modules enum and selective checkpoint logic\n\n```python\n# 3rdparty\u002FMegatron-LM\u002Fmegatron\u002Fcore\u002Ftransformer\u002Ftransformer_block.py\n# _checkpointed_forward() applies selective recompute based on recompute_modules\n```\n\n### Recompute config validation\n\n```python\n# 3rdparty\u002FMegatron-LM\u002Fmegatron\u002Fcore\u002Ftransformer\u002Ftransformer_config.py\n# Validates recompute_granularity, recompute_method, recompute_num_layers\n```\n\n### Llama3 recipe defaults\n\n```99:103:src\u002Fmegatron\u002Fbridge\u002Frecipes\u002Fllama\u002Fllama3.py\n    # Memory saving (recompute & offloading)\n    cfg.model.recompute_granularity = None\n    cfg.model.recompute_modules = None\n    cfg.model.fine_grained_activation_offloading = False\n    cfg.model.offload_modules = None\n```\n\n### Full recompute + CUDA graph assertion (MCore)\n\n```2001:2005:3rdparty\u002FMegatron-LM\u002Fmegatron\u002Fcore\u002Ftransformer\u002Ftransformer_config.py\n            if self.recompute_granularity:\n                if self.recompute_granularity != \"selective\":\n                    assert self.cuda_graph_scope == [\n                        CudaGraphScope.full_iteration\n                    ], \"full recompute is only supported with full iteration CUDA graph.\"\n```\n\n### CPU offloading PP incompatibility (MCore)\n\n```1303:1306:3rdparty\u002FMegatron-LM\u002Fmegatron\u002Fcore\u002Ftransformer\u002Ftransformer_config.py\n        if self.cpu_offloading and self.pipeline_model_parallel_size > 1:\n            raise ValueError(\n                \"Currently there is no support for Pipeline parallelism with CPU offloading\"\n            )\n```\n\n## Failure Diagnosis\n\n| Symptom | Cause | Confirm | Fix |\n|---|---|---|---|\n| >15% GPU utilization drop | `mlp` recompute on a large FFN | check whether `recompute_modules` includes `mlp` | remove `mlp`, lower micro batch size, or use CPU offload if PP=1 |\n| Still OOM after adding layernorm | layernorm activations are too small to move the peak materially | compare peak memory before\u002Fafter | switch to a higher-impact module or full-layer recompute |\n| `AssertionError: full recompute is only supported with full iteration CUDA graph` | layer-level recompute with TE-scoped graph capture | check `cuda_graph_impl` and `cuda_graph_scope` | use `selective`, set `cuda_graph_impl=none`, or use `local` + `full_iteration` |\n| ValueError: PP + CPU offloading | `cpu_offloading=True` with `pipeline_model_parallel_size > 1` | check PP config | disable CPU offloading or set PP=1 |\n| mlp+core_attn worse than mlp alone | double recompute overhead | compare Exp 1 vs Exp 2 | use mlp alone |\n\n## Known Limitations\n\n- Per-module memory savings vary significantly by model architecture and hidden\n  dimension\n- No automatic module selection — users must choose which modules to recompute\n- `layernorm` recompute is almost never worth it as a standalone fix\n- CPU offloading (the zero-compute-cost alternative) is blocked when PP > 1\n\n## Verification\n\n```bash\nuv run python -m pytest \\\n  tests\u002Funit_tests\u002Ftraining\u002Ftest_config.py -k \"recompute\" -q\n```\n\nSuccess criteria:\n- Unit tests pass for recompute config validation\n- No assertion errors from config validation\n",{"name":5,"license":15,"description":7,"when_to_use":24},"Reducing GPU memory via activation recompute, or investigating a commit that changed recompute settings and caused OOM or a regression; 'recompute_granularity', 'recompute_num_layers', 'recompute_modules', 'recompute_method', 'selective recompute', 'full recompute', 'activation memory OOM'.","main","1c523aba5cdf867a79f078847075492d7778092a","skills\u002Fnvidia\u002Fnemo-mbridge-perf-activation-recompute",1,"https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills","https:\u002F\u002Fskills.x402.wtf","https:\u002F\u002Fgithub.com\u002Fthemusebook","https:\u002F\u002Fmusebook.trade","The official Github of musebook","2026-11-02 23:42:26",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add themusebook\u002Fskills --skill nemo-mbridge-perf-activation-recompute",{"tool":41,"command":42},"bunx","bunx skills add themusebook\u002Fskills --skill nemo-mbridge-perf-activation-recompute",{"tool":44,"command":45},"pnpm","pnpm dlx skills add themusebook\u002Fskills --skill nemo-mbridge-perf-activation-recompute","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-mbridge-perf-activation-recompute\u002FSKILL.md",true,[49,55,59,63,67],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"BENCHMARK.md","REFERENCE","参考文档",4036,"https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-mbridge-perf-activation-recompute\u002FBENCHMARK.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"card.yaml",7920,"https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-mbridge-perf-activation-recompute\u002Fcard.yaml",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"evals\u002Fevals.json",1720,"https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-mbridge-perf-activation-recompute\u002Fevals\u002Fevals.json",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"skill-card.md",3814,"https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-mbridge-perf-activation-recompute\u002Fskill-card.md",{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"skill.oms.sig","OTHER","其他",4833,"https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-mbridge-perf-activation-recompute\u002Fskill.oms.sig",[74,83,90,97,104,111],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":79,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7AB34SPKVSDRRG009PM1CZH","youtube-clipper","YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。 使用场景：当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词：视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video","MIT","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-clipper\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-clipper\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7AB18BH6N7KR7939HRNWVMQ","viem-integration","Integrate EVM blockchains using viem. Use when user says \"read blockchain data\", \"send transaction\", \"interact with smart contract\", \"connect to Ethereum\", \"use viem\", \"use wagmi\", \"wallet integration\", \"viem setup\", or mentions blockchain\u002FEVM development with TypeScript.","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fviem-integration\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7AB12GHGP48WCNXDQQ9222H","v4-security-foundations","Security-first Uniswap v4 hook development. Use when user mentions \"v4 hooks\", \"hook security\", \"PoolManager\", \"beforeSwap\", \"afterSwap\", or asks about V4 hook best practices, vulnerabilities, or audit requirements.","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fv4-security-foundations\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M7AB0XM3PSR7V3Q2ZRR0Q0FB","v4-sdk-integration","App-layer SDK guide for building swap and liquidity experiences directly with the Uniswap v4 SDK. Use when user asks about \"v4 sdk\", \"uniswap v4\", \"v4 swap\", \"v4 liquidity\", \"PoolManager\", \"V4Planner\", \"StateView\", \"PositionManager\", \"pool state\", \"v4 position\", \"uniswap sdk\", or when building swap\u002Fliquidity UX directly with SDKs rather than via the Trading API.","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fv4-sdk-integration\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M7AB0SGA93ASA588DJW4P9WT","v4-hook-generator","Generate Uniswap v4 hook contracts via OpenZeppelin MCP. Use when building custom swap logic, async swaps, hook-owned liquidity, custom curves, dynamic fees, MEV protection, limit orders, or oracle hooks.","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fv4-hook-generator\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":19},"01M7AAZYH75H4CS03WSW2EZ8DM","testing","For testing with Light Protocol programs and clients on localnet, devnet, and mainnet validation.","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftesting\u002FSKILL.md",[],[]]