Results for “salmon”

Optimizes Qdrant query performance for large limits across multiple shards by using Poisson-distributed subsampling to reduce inter-shard data transfer.

Serve LLMs and VLMs on NVIDIA Jetson devices using vLLM or SGLang with optimized Docker containers and quantization presets.

Use when SWMM integration, API development, or data synchronization is needed. This agent specializes in SWMM connectivity within the IntegrateForge AI ecosystem.

Ableton Live Object Model (LOM) API reference for Python Remote Scripts and control surface development.

Runs Stanford's STORM pipeline to produce Wikipedia-quality research articles with citations, using Claude models and a search engine API.

Post-train LLMs with reinforcement learning using the slime framework, which integrates Megatron-LM for training and SGLang for rollout generation.

SA-1B: Segment Anything 1 Billion Masks Dataset

Drive Soup (`soup-cli`), a CLI-first tool for fine-tuning and post-training LLMs with one YAML config and one command — SFT, DPO/GRPO/ORPO/SimPO/KTO, QLoRA/DoRA/LoRA+, layer streaming for 4-8 GB GPUs, eval-gated training, and serving. Use when the user wants to `soup init`/`soup train` a model, pick a training method or quantization scheme, estimate cost/memory before training, fine-tune on a small local GPU, migrate a config from Axolotl/LLaMA-Factory/Unsloth, or serve/merge/push a trained adapter. Triggers on: "soup-cli", "soup train", "soup init", "fine-tune an LLM locally", "QLoRA on a laptop GPU", "layer streaming", "soup advise", "soup autopilot", "DPO/GRPO/ORPO training", "merge LoRA adapter".

Context compression for YAMTAM — nén JSON/structured tool output trước khi vào LLM. Hiệu quả với JSON (50-72% tiết kiệm); text thuần cần bản [all].

Evaluates how well internal model representations (hidden states) predict token-level information importance in summarization tasks, using NDCG@10 and Spearman's rank correlation.

Scrapes pump.fun/board using Chrome browser automation to extract the top 100 trending Solana tokens and writes structured markdown for a trading agent to consume. Use this skill any time you need to: scan pump.fun for new tokens, refresh the pump.md token list, run the scheduled board scrape, collect Solana meme token data, or build/update a trading watchlist from pump.fun. Even if the user says something casual like "check pump" or "update the token list" or "what's trending on pump", use this skill. The output file path and format are configurable but default to /Users/8bit/solanaos/pump.md.

Server-Sent Events for real-time server-to-client streaming. Express, Fastify, FastAPI, Spring WebFlux SSE implementations. Event streams, reconnection, and EventSource API. USE WHEN: user mentions "SSE", "Server-Sent Events", "EventSource", "event stream", "text/event-stream", "live feed", "streaming updates" DO NOT USE FOR: bidirectional communication - use `socket-io`; WebRTC - use `webrtc`; LLM streaming - use AI SDK skills

Runs large language models locally with Ollama, including model management, custom Modelfiles, and API integration. Use for private, offline LLM inference.