Popular repositories Loading

1. note-seq note-seq Public

   Forked from magenta/note-seq

   A serializable note sequence representation and utilities.

   Python

2. magenta magenta Public

   Forked from magenta/magenta

   Magenta: Music and Art Generation with Machine Intelligence

   Python

3. gpu-inference-benchmarks gpu-inference-benchmarks Public

   Reproducible GPU inference serving benchmarks across models and runtimes.

   Python

4. qwen38-mtp qwen38-mtp Public

   Forked from sudoingX/qwen38-mtp

   One llama.cpp flag unlocks +33-39% decode speed for Qwen3.8-27B on consumer GPUs. The MTP head already ships inside your GGUF. Recipe, paired benchmarks, probe tool.

   Python

5. glm-5.3-flash-4x-rtx-pro-6000-benchmark glm-5.3-flash-4x-rtx-pro-6000-benchmark Public

   GLM-5.3-Flash on four RTX PRO 6000 Blackwell GPUs: benchmarks of TensorFold, the vLLM fork by local-inference-lab (Jovian Judgement), and official vLLM 0.31.0, with data, probes, and raw output.

   Python

6. integer-mult-bounds integer-mult-bounds Public

   Forked from CrocSwap/integer-mult-bounds

   Conditional integer multiplication: kappa > 2^-15. Community proofs, exact certificates and reproducible audits; assumes the OpenAI #109 framework.

   Python