Commits

Commit history

1. Commits on Oct 4, 2024

   • Vllm 0.6.0 integration test (#10697)

     Show description for 3578f75
     

     HuiyingLi

     and

     oyilmaz-nvidia

     authored
     3578f75View commit details

     Copy full SHA for 3578f75

     View code at this pointBrowse repository at this point
2. Commits on Sep 19, 2024

   • Update inference tests scripts and models (#10505)

     Show description for 28851be
     

     janekl

     and

     oyilmaz-nvidia

     authored
     28851beView commit details

     Copy full SHA for 28851be

     View code at this pointBrowse repository at this point
3. Commits on Aug 30, 2024

   • Flexible passing args to TensorRTLLM in nemo_export.py (#10315)

     Show description for 1ce9089
     janekl

     authored
     1ce9089View commit details

     Copy full SHA for 1ce9089

     View code at this pointBrowse repository at this point
4. Commits on Aug 29, 2024

   • Export fp8 te nemo to trt-llm (#10096)

     Show description for 9796b69
     Laplasjan107

     authored
     9796b69View commit details

     Copy full SHA for 9796b69

     View code at this pointBrowse repository at this point
5. Commits on Aug 19, 2024

   • Remove max_num_tokens heuristic from test scripts (#10074)

     Show description for ff77789
     janekl

     authored
     ff77789View commit details

     Copy full SHA for ff77789

     View code at this pointBrowse repository at this point
6. Commits on Jul 26, 2024

   • Integrate TRT-LLM v0.11 (#9705)

     Show description for c81f7cf
     oyilmaz-nvidia

     authored
     c81f7cfView commit details

     Copy full SHA for c81f7cf

     View code at this pointBrowse repository at this point
7. Commits on Jul 9, 2024

   • Triton deployment improvements for in-framework models (#9600)

     Show description for 8898b76
     

     jukim-nv

     and

     oyilmaz-nvidia

     authored
     8898b76View commit details

     Copy full SHA for 8898b76

     View code at this pointBrowse repository at this point
8. Commits on Jul 3, 2024

   • vLLM Export Improvements (#9596)

     Show description for 590b762
     

     3 peopleauthored
     590b762View commit details

     Copy full SHA for 590b762

     View code at this pointBrowse repository at this point
9. Commits on Jul 2, 2024

   • Set n_gpu to None in nemo export (#9593)

     Show description for 5a9000f
     oyilmaz-nvidia

     authored
     5a9000fView commit details

     Copy full SHA for 5a9000f

     View code at this pointBrowse repository at this point
10. Commits on Jul 1, 2024

    • PTQ refinements (#9574)

      Show description for f64e77d
      janekl

      authored
      f64e77dView commit details

      Copy full SHA for f64e77d

      View code at this pointBrowse repository at this point
11. Commits on Jun 28, 2024

    • Add tps and pps params to the export script (#9558)

      Show description for ba1968f
      oyilmaz-nvidia

      authored
      ba1968fView commit details

      Copy full SHA for ba1968f

      View code at this pointBrowse repository at this point
12. Commits on Jun 27, 2024

    • Fix nemo export test (#9547)

      Show description for 392b4ad
      

      oyilmaz-nvidia

      and

      pablo-garay

      authored
      392b4adView commit details

      Copy full SHA for 392b4ad

      View code at this pointBrowse repository at this point
13. Commits on Jun 26, 2024

    • Test C++ runtime on demand in nemo_export.py to avoid possible OOMs (#9544)

      Show description for 362b894
      janekl

      authored
      362b894View commit details

      Copy full SHA for 362b894

      View code at this pointBrowse repository at this point
14. Commits on Jun 25, 2024

    • vLLM Export Support (#9381)

      Show description for 9e979d4
      

      3 peopleauthored
      9e979d4View commit details

      Copy full SHA for 9e979d4

      View code at this pointBrowse repository at this point
15. Commits on Jun 13, 2024

    • TRT-LLM 0.10 Update (#9402)

      Show description for a72a0e7
      

      oyilmaz-nvidia

      and

      meatybobby

      authored
      a72a0e7View commit details

      Copy full SHA for a72a0e7

      View code at this pointBrowse repository at this point
16. Commits on Jun 10, 2024

    • Use TensorRT-LLM native parameter names in nemo.export module (#9424)

      Show description for 69954ef
      janekl

      authored
      69954efView commit details

      Copy full SHA for 69954ef

      View code at this pointBrowse repository at this point
17. Commits on May 30, 2024

    • Fix P-tuning for Llama based models (#9300)

      Show description for b6595cb
      

      4 peopleauthored
      b6595cbView commit details

      Copy full SHA for b6595cb

      View code at this pointBrowse repository at this point
18. Commits on May 21, 2024

    • Add TRT-LLM params like max_num_tokens and opt_num_tokens (#9210)

      Show description for 2e1814c
      

      oyilmaz-nvidia

      and

      pablo-garay

      authored
      2e1814cView commit details

      Copy full SHA for 2e1814c

      View code at this pointBrowse repository at this point
19. Commits on May 16, 2024

    • Add save option to the TRT-LLM export test script (#9221)

      Show description for e465b9c
      oyilmaz-nvidia

      authored
      e465b9cView commit details

      Copy full SHA for e465b9c

      View code at this pointBrowse repository at this point
20. Commits on Apr 24, 2024

    • update gemme for trt-llm 0.9 (#8974)

      Show description for b0bb807
      

      oyilmaz-nvidia

      and

      pablo-garay

      authored
      b0bb807View commit details

      Copy full SHA for b0bb807

      View code at this pointBrowse repository at this point
21. Commits on Apr 23, 2024

    • Quantized checkpoint support in export and deploy modules (#8859)

      Show description for 571a425
      

      3 peopleauthored
      571a425View commit details

      Copy full SHA for 571a425

      View code at this pointBrowse repository at this point
22. Commits on Apr 6, 2024

    • Open source export and deploy modules (#8743)

      Show description for 97d1abb
      

      3 peopleauthored
      97d1abbView commit details

      Copy full SHA for 97d1abb

      View code at this pointBrowse repository at this point
23. Loading