Search
SGLang · For data scientists
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones. | huggingface/ | 11k | 1 repo | ~4.6k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 2 | Write, calibrate, and debug the prefill-vs-decode logprob (KL) consistency tests in sglang -- the two independent conditions a zero requires (every operator batch-invariant, and the two paths… | sgl-project/ | 37k | 2 repos | ~3.7k | Automated safety check: Pass | Apache-2.0 | today |
| 3 | Clean up noisy startup warnings and spurious prints in SGLang server logs. | guqiong96/ | 144 | 1 repo | ~4.5k | Automated safety check: Pass | Apache-2.0 | 6 days ago |
| 4 | Trigger the bot-cherry-pick workflow for a batch of merged PRs onto a release branch and monitor each run to completion. | sgl-project/ | 37k | 2 repos | ~4k | Automated safety check: Pass | Apache-2.0 | today |
| 5 | Diagnose and correct GPT-QModel tokenizer initialization, tokenization normalization, special-token handling, prompt rendering, and chat-template problems. | ModelCloud/ | 1.3k | — | ~1.1k | Automated safety check: Pass | Unknown | today |
| 6 | A skill your agent uses when quantizing a diffusion DiT with NVIDIA ModelOpt and making the resulting FP8 or NVFP4 checkpoint loadable, verifiable, and benchmarkable in SGLang Diffusion. | sgl-project/ | 37k | 2 repos | ~5k | Automated safety check: Pass | Apache-2.0 | today |
| 7 | Guides reinforcement-learning post-training of LLMs with slime, which pairs Megatron-LM training with SGLang rollouts, including GRPO runs on GLM, Qwen3 and Llama 3 models. | Orchestra-Research/ | 13k | 4 repos | ~2.8k | Automated safety check: Pass | MIT | 3 mo ago |
| 8 | A skill your agent uses when choosing the fastest SGLang Diffusion flags for a model, GPU, and VRAM budget. | sgl-project/ | 37k | 2 repos | ~13k | Automated safety check: Pass | Apache-2.0 | today |
| 9 | Requirements for the SGLang scripted runtime, chiefly when to add (vs not add) a harness API. | sgl-project/ | 37k | 2 repos | ~448 | Automated safety check: Pass | Apache-2.0 | today |
| 10 | A skill your agent uses when adding a new diffusion model or Diffusers pipeline to SGLang. | sgl-project/ | 37k | 2 repos | ~9.9k | Automated safety check: Pass | Apache-2.0 | today |
| 11 | Covers serving LLMs with SGLang, whose RadixAttention reuses cached prefixes, and constraining output to JSON, regex or grammar for agent and tool-calling workloads. | Orchestra-Research/ | 13k | 2 repos | ~2.9k | Automated safety check: Pass | MIT | 3 mo ago |
| 12 | Trains LLMs with reinforcement learning using verl, from ByteDance's Seed team, with GRPO, PPO and other algorithms and swappable training and rollout backends. | Orchestra-Research/ | 13k | 2 repos | ~2.4k | Automated safety check: Pass | MIT | 3 mo ago |
| 13 | How SGLang's runtime configuration and process-global state are organized (RuntimeContext tiers, publish + namespace config bags, the pristine ServerArgs seed, override entry points… | sgl-project/ | 37k | 2 repos | ~11k | Automated safety check: Pass | Apache-2.0 | today |
| 14 | Audit the existing test tree and CI configuration for improvements, using a catalog of patterns previously applied in this repo. | sgl-project/ | 37k | — | ~520 | Automated safety check: Pass | Apache-2.0 | today |
| 15 | Apply the SGLang kernels RFC when adding, moving, splitting, or reviewing kernel APIs, registry metadata, kernel tests, benchmarks, and model-specific implementations. | sgl-project/ | 37k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | today |