8000 Comparing main...0.6.2.post1 · InternLM/lmdeploy · GitHub
[go: up one dir, main page]
Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: InternLM/lmdeploy
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: main
Choose a base ref
...
head repository: InternLM/lmdeploy
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: 0.6.2.post1
Choose a head ref
Checking mergeability… Don’t worry, you can still create the pull request.
  • 10 commits
  • 28 files changed
  • 7 contributors

Commits on Nov 5, 2024

  1. fix turbomind TP for v0.6.2 (#2713)

    @lzhangzz
    lzhangzz authored Nov 5, 2024
    Configuration menu
    10000
    Copy the full SHA
    5ea819f View commit details
    Browse the repository at this point in the history

  2. Call cuda empty_cache to prevent OOM when quantizing model (#2671) 

    * Call cuda empty_cache to prevent OOM when quantizing model

* empty cache during export and after forward
    @AllentDan @lvhan028
    AllentDan authored and lvhan028 committed Nov 5, 2024
    Configuration menu
    Copy the full SHA
    28c8b79 View commit details
    Browse the repository at this point in the history

  3. fix ascend get_started.md link (#2696) 

    * fix ascend get_started.md link

* fix en ascend get_started.md
    @CyCle1024 @lvhan028
    CyCle1024 authored and lvhan028 committed Nov 5, 2024
    Configuration menu
    Copy the full SHA
    02cb173 View commit details
    Browse the repository at this point in the history

  4. Support min_tokens, min_p parameters for api_server (#2681) 

    * Support min_tokens for api_server

* fix

* use min_new_tokens

* add min_p
    @AllentDan @lvhan028
    AllentDan authored and lvhan028 committed Nov 5, 2024
    Configuration menu
    Copy the full SHA
    1d2b9c6 View commit details
    Browse the repository at this point in the history

  5. fix index error when computing ppl on long-text prompt (#2697) 

    * fix index error when computing ppl on long-text prompt

* update user guide
    @lvhan028
    lvhan028 committed Nov 5, 2024
    Configuration menu
    Copy the full SHA
    58c9126 View commit details
    Browse the repository at this point in the history

  6. better tp exit log (#2677)

    @grimoire @lvhan028
    grimoire authored and lvhan028 committed Nov 5, 2024
    Configuration menu
    Copy the full SHA
    36bf28f View commit details
    Browse the repository at this point in the history

  7. miss to read moe_ffn weights from converted tm model (#2698) 

    * miss to read moe_ffn weights

* fix linting

* fix linting

* fix linting
    @lvhan028
    lvhan028 committed Nov 5, 2024
    Configuration menu
    Copy the full SHA
    f33a639 View commit details
    Browse the repository at this point in the history

  8. Fix llama3.2 VL vision in "Supported Modals" documents (#2703) 

    * fix zh_cn supported_models.md llama3.2 version

* fix zh_cn supported_models.md llama3.2 version
    @blankanswer @lvhan028
    blankanswer authored and lvhan028 committed Nov 5, 2024
    Configuration menu
    Copy the full SHA
    177da9b View commit details
    Browse the repository at this point in the history

  9. [ci] support v100 dailytest (#2665) 

    * update

* update

* update

* update

* update
    @zhulinJulia24 @lvhan028
    zhulinJulia24 authored and lvhan028 committed Nov 5, 2024
    Configuration menu
    Copy the full SHA
    434195e View commit details
    Browse the repository at this point in the history

Commits on Nov 7, 2024

  1. bump version to 0.6.2.post1 (#2717)

    @lvhan028
    lvhan028 authored Nov 7, 2024
    Configuration menu
    Copy the full SHA
    4fc9479 View commit details
    Browse the repository at this point in the history
Loading
0