diff --git a/.github/workflows/book-ci.yml b/.github/workflows/book-ci.yml index f09f18a..61f5f56 100644 --- a/.github/workflows/book-ci.yml +++ b/.github/workflows/book-ci.yml @@ -4,12 +4,12 @@ on: push: branches: - main - - server_support + # - server_support pull_request: branches: - main - - server_support + # - server_support jobs: test: name: test diff --git a/.github/workflows/deploy.yml b/.github/workflows/deploy.yml index f9f8341..4a8de5e 100644 --- a/.github/workflows/deploy.yml +++ b/.github/workflows/deploy.yml @@ -42,7 +42,8 @@ jobs: # ci/copy-assets.sh ${{ matrix.os }} - name: Deploy uses: peaceiris/actions-gh-pages@v3 - if: ${{ github.ref == 'refs/heads/main' }} or || github.ref == 'refs/heads/server_support' + # or || github.ref == 'refs/heads/server_support' + if: ${{ github.ref == 'refs/heads/main' }} with: github_token: ${{ secrets.GITHUB_TOKEN }} publish_dir: ./book \ No newline at end of file diff --git a/doc/SUMMARY.md b/doc/SUMMARY.md index 449e0f6..7645018 100644 --- a/doc/SUMMARY.md +++ b/doc/SUMMARY.md @@ -2,13 +2,19 @@ [Introduction](./README.md) # DeepSeek -- [DeepseekR1_V3_tutorial](en/DeepseekR1_V3_tutorial.md) -- [deepseek-v2-injection](en/deepseek-v2-injection.md) -- [Makefile_usage](en/makefile_usage.md) +- [Deepseek-R1/V3 Tutorial](en/DeepseekR1_V3_tutorial.md) +- [Deepseek-V2 Injection](en/deepseek-v2-injection.md) +- [Injection Tutorial](en/injection_tutorial.md) + # Server - [Server](zh/api/server/README.md) - - [Server](zh/api/server/server.md) + - [Server](en/api/server/server.md) - [Website](zh/api/server/website.md) - [Tabby](zh/api/server/tabby.md) +# For Developer +- [For Developer](en/injection_tutorial.md) + # FAQ -- [FAQ](en/FAQ.md) \ No newline at end of file +- [FAQ](en/FAQ.md) +# V3 Reproduction +- [Success List](en/V3-success.md) \ No newline at end of file diff --git a/doc/en/V3-success.md b/doc/en/V3-success.md new file mode 100644 index 0000000..af69f27 --- /dev/null +++ b/doc/en/V3-success.md @@ -0,0 +1,10 @@ +## Hello everyone, here is the successfully reproduced environment configuration for your reference: +### Case 1 +- Configuration: l40s 48G + 9654 x2 (192 cores) + 768G DDR5 12-channel +- Performance: prefill 108 tokens/s, decode 10.8 tokens/s +- Used version: main source code compiled +### Case 2 +- Configuration: Dual Xeon 6430 32C processors, totaling 64 cores and 128 threads, 480GB DDR5 memory, single 4090 24G graphics card +- Performance: Running speed approximately 6-8 tokens per second +# NOTE +If there are any other configurations that have been successfully run, please feel free to let us know. We will keep updating for everyone to refer to when reproducing. (It has been found that it also works on 2080, AMD, etc. (doge : ) https://docs.qq.com/smartsheet/form/AVxgQOYhhNfl%2FBB08J2%2Fv3rnnq?tab=BB08J2 \ No newline at end of file