Min memory (2.05GB), higher FPS (1.6x), balanced mode — pick whichever you like.

Open
#80 2 comments 4 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
35/100
Issue type
Feature
Clarity
Needs clarification
Activity status
Quiet
Tech stack
python

Research direction

No target file or test is named. Start by reviewing the linked rtx4060_8g branch and reproducing the keble-college-02 baseline with the listed flags; done would require selecting an optimization, integrating it, and documenting its memory, FPS, ATE, and trajectory-smoothness results.

Written by the indexing model from the issue text.

Description

I experimented with a few optimizations: weight/activation quantization, KV cache quantization, and KV cache downsampling.
Tests were conducted on an RTX 4060 Laptop GPU.
Baseline scene: keble-college-02, streaming mode with flags --first_k 320 --num_scale_frames 2 --kv_cache_sliding_window 48.
More details are available here: https://github.com/ureeey/lingbot-map-rtx4060-8g/tree/rtx4060_8g.

摘要 权重激活量化 KV Cache fp8 量化 KV Cache 下采样 显存峰值(GB) FPS ATE 轨迹平滑
基准 禁用 禁用 禁用 7.13 3.6 基准 基准
单项分析 int4、int8混合 - - 5.37 2.2 轻微变化 轻微变化
单项分析 fp8 - - 5.68 3.7 轻微变化 显著变差
单项分析 - 启用 - 5.17 3.3 轻微变化 轻微变化
单项分析 - - 启用 4.4 5.4 显著变差 轻微变化
最小内存 int4、int8混合 启用 启用 2.05 2.7 显著变差 轻微变化
最快 fp8 - 启用 2.96 5.8 显著变差 显著变差
平衡 int4、int8混合 启用 - 3.41 2.1 轻微变化 轻微变化
Dominant language
Python
Stars
17.1k
Forks
1.9k
PR merge metrics
No merged PRs in 30d

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from Robbyant/lingbot-map

All issues in Robbyant/lingbot-map

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.