Sign in

Repository Index

142,273 visible repositories in the index

Tags: All Tags
Tags

A repository shows when it has any selected Tag.

Filters (1)

Filters

Clear all filters

25–48 of 119 · Most stars

Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.

A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-write fork ~5x faster than docker commit, with ~95% KV-cache reuse on replay. Framework built for meta-agents to supervise, optimize, and train other agents

Official SGLang x Datawhale course on LLM inference: understand inference, build a mini-sglang from scratch, then read the real SGLang source and land your first PR. Available in English and Chinese.

TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration

:blue_book: dict subclass with keylist/keypath support, built-in I/O operations (base64, csv, html, ini, json, pickle, plist, query-string, toml, xls, xml, yaml), s3 support and many utilities.

  • python
  • dict
  • dictionary
  • keypath

TranslatedA Claude Code skill that digs into an unfamiliar field in a sweet-potato-vine fashion, one lead pulling up the next, until it reaches the original source text

A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for DiTs.

  • flux2-klein
  • svdquant
  • flux3
  • flux3-klein