Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add StreamingLLM support to studio2 chat #2060

Merged
merged 23 commits into from
Jan 19, 2024
Merged

Add StreamingLLM support to studio2 chat #2060

merged 23 commits into from
Jan 19, 2024

Commits on Jan 9, 2024

  1. Streaming LLM (WIP)

    @monorimet
    monorimet committed Jan 9, 2024
    Configuration menu
    Copy the full SHA
    f6b249a View commit details
    Browse the repository at this point in the history

  2. Update precision and add gpu support

    @monorimet
    monorimet committed Jan 9, 2024
    Configuration menu
    Copy the full SHA
    353d50f View commit details
    Browse the repository at this point in the history

  3. (studio2) Separate weights generation for quantization support

    @monorimet
    monorimet committed Jan 9, 2024
    Configuration menu
    Copy the full SHA
    ee53971 View commit details
    Browse the repository at this point in the history

  4. Small fixes to prompts, weights gen

    @monorimet
    monorimet committed Jan 9, 2024
    Configuration menu
    Copy the full SHA
    79460ef View commit details
    Browse the repository at this point in the history

  5. Adapt prompt changes to studio flow

    @monorimet
    monorimet committed Jan 9, 2024
    Configuration menu
    Copy the full SHA
    8283054 View commit details
    Browse the repository at this point in the history

  6. Final commit

    @monorimet
    monorimet committed Jan 9, 2024
    Configuration menu
    Copy the full SHA
    a7b2231 View commit details
    Browse the repository at this point in the history

  7. Update utils.py

    @monorimet
    monorimet authored Jan 9, 2024
    Configuration menu
    Copy the full SHA
    f456e87 View commit details
    Browse the repository at this point in the history

  8. Remove outdated flag from llm compile flags.

    @monorimet
    monorimet committed Jan 9, 2024
    Configuration menu
    Copy the full SHA
    df78dec View commit details
    Browse the repository at this point in the history

  9. (studio2) use turbine vmfbRunner

    @monorimet
    monorimet committed Jan 9, 2024
    Configuration menu
    Copy the full SHA
    163241a View commit details
    Browse the repository at this point in the history

Commits on Jan 10, 2024

  1. fix streaming

    @monorimet
    monorimet committed Jan 10, 2024
    Configuration menu
    Copy the full SHA
    3ac56ad View commit details
    Browse the repository at this point in the history

  2. bugfixes

    @monorimet
    monorimet committed Jan 10, 2024
    Configuration menu
    Copy the full SHA
    a099d76 View commit details
    Browse the repository at this point in the history

  3. Fix stopping

    @monorimet
    monorimet committed Jan 10, 2024
    Configuration menu
    Copy the full SHA
    32e712b View commit details
    Browse the repository at this point in the history

  4. tweaks to prompts

    @monorimet
    monorimet committed Jan 10, 2024
    Configuration menu
    Copy the full SHA
    ead1715 View commit details
    Browse the repository at this point in the history

Commits on Jan 16, 2024

  1. Update CPU path and llm api test.

    @monorimet
    monorimet committed Jan 16, 2024
    Configuration menu
    Copy the full SHA
    c195dd6 View commit details
    Browse the repository at this point in the history

  2. Fix formatting.

    @monorimet
    monorimet committed Jan 16, 2024
    Configuration menu
    Copy the full SHA
    a788e12 View commit details
    Browse the repository at this point in the history

  3. Remove unused function.

    @monorimet
    monorimet committed Jan 16, 2024
    Configuration menu
    Copy the full SHA
    c48c562 View commit details
    Browse the repository at this point in the history

  4. Change device in test to cpu.

    @monorimet
    monorimet committed Jan 16, 2024
    Configuration menu
    Copy the full SHA
    643214d View commit details
    Browse the repository at this point in the history

Commits on Jan 17, 2024

  1. Fixes to runner, device names, vmfb mgmt

    @monorimet
    monorimet committed Jan 17, 2024
    Configuration menu
    Copy the full SHA
    dccd585 View commit details
    Browse the repository at this point in the history

  2. Only run small tests.

    @monorimet
    monorimet committed Jan 17, 2024
    Configuration menu
    Copy the full SHA
    1ed5543 View commit details
    Browse the repository at this point in the history

  3. Use small test without external weights.

    @monorimet
    monorimet committed Jan 17, 2024
    Configuration menu
    Copy the full SHA
    9ff8fa7 View commit details
    Browse the repository at this point in the history

  4. remove redundant compile flags

    @monorimet
    monorimet authored Jan 17, 2024
    Configuration menu
    Copy the full SHA
    ed780b0 View commit details
    Browse the repository at this point in the history

  5. remove print of prompt prefix

    @monorimet
    monorimet authored Jan 17, 2024
    Configuration menu
    Copy the full SHA
    29c40f4 View commit details
    Browse the repository at this point in the history

  6. Fix flags.

    @monorimet
    monorimet committed Jan 17, 2024
    Configuration menu
    Copy the full SHA
    0c6e5ca View commit details
    Browse the repository at this point in the history