Search
AI & LLM Engineering · By intel
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Adapt AutoRound to support a new diffusion model architecture (DiT, UNet, hybrid AR+DiT). | intel/ | 1.6k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 2 | Adapt AutoRound to support a new LLM architecture that doesn't work out-of-the-box. | intel/ | 1.6k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 3 | Add a new model export format to AutoRound (e.g., autoround, autogptq, autoawq, gguf, llmcompressor). | intel/ | 1.6k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 4 | Add a new hardware inference backend to AutoRound for deploying quantized models (e.g., CUDA/Marlin, Triton, CPU, HPU, ARK). | intel/ | 1.6k | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 5 | Add a new quantization data type to AutoRound (e.g., INT, FP8, MXFP, NVFP, GGUF variants). | intel/ | 1.6k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 6 | Add support for a new Vision-Language Model (VLM) to AutoRound, including multimodal block handler, calibration dataset template, and special model handling. | intel/ | 1.6k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 7 | Check PyTorch ciflow/xpu (xpu.yml) on the main branch, collect the failing XPU test cases from the most recent completed run(s), analyze the ROOT CAUSE of each failure with AI, and produce a list… | intel/ | 115 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | today |
| 8 | Review or prepare a pull request for the AutoRound repository — checks registration points for new data types/backends/VLMs, validates Chinese translation parity for modified markdown files… | intel/ | 1.6k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 9 | Convert PyTorch ATDISPATCH macros to ATDISPATCHV2 format in ATen C++ code. | intel/ | 115 | 3 repos | ~2.2k | Automated safety check: Pass | Apache-2.0 | today |
| 10 | Review PyTorch upstream unit-test (UT) PRs that enable Intel GPU (XPU) on existing tests. | intel/ | 115 | — | ~917 | Automated safety check: Pass | Apache-2.0 | today |
| 11 | Extract GPU ISA from Triton kernels on XPU. An agent skill from intel/torch-xpu-ops. | intel/ | 115 | — | ~806 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 12 | Extract Intel GPU ISA (assembly) from any XPU kernel. An agent skill from intel/torch-xpu-ops. | intel/ | 115 | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 13 | A skill your agent uses when asked to implement a fix for a root-caused failure, apply a proposed patch, or produce a staged code change from triage output. | intel/ | 115 | — | ~4.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 14 | A skill your agent uses when asked to verify a fix works, confirm a staged patch resolves a failure, or produce a before/after summary of a fix. | intel/ | 115 | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 15 | A skill your agent uses when setting up a new torch-xpu-ops release branch corresponding to a PyTorch release. | intel/ | 115 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 16 | Build PyTorch from source with Intel XPU (GPU) support. An agent skill from intel/torch-xpu-ops. | intel/ | 115 | — | ~939 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 17 | Generate and analyze T1/T2/R roofline reports for PyTorch OOB workloads comparing Intel XPU and NVIDIA CUDA. | intel/ | 115 | — | ~681 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 18 | Find upstream PyTorch behavior or fixes that may require XPU parity work, validate them on XPU, and produce independently reviewed evidence. | intel/ | 115 | — | ~2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 19 | A skill your agent uses when asked to reproduce a bug, verify a nightly CI failure, or confirm a failure still exists on latest source. | intel/ | 115 | — | ~7.7k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 20 | Shallow, text-only triage of a GitHub issue on pytorch or torch-xpu-ops. | intel/ | 115 | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
