Code

TRT LLM Integration with LORA#3305

Code

Merged

mreso merged 20 commits intomasterpytorch/serve:masterfrom feature/trt_llm_lorapytorch/serve:feature/trt_llm_loraCopy head branch name to clipboardSep 17, 2024

+428-173

Commits

Commits on Sep 6, 2024

• TRT LLM Integration with LORA

  agunapal

  committed
  98b654f

• TRT LLM Integration with LORA

  agunapal

  committed
  ce59497

• TRT LLM Integration with LORA

  agunapal

  committed
  347159f

• TRT LLM Integration with LORA

  agunapal

  committed
  06d5b47

Commits on Sep 7, 2024

• Added launcher support for trt_llm

  agunapal

  committed
  0ecc71a

• updated README

  agunapal

  committed
  56d0ccc

• updated README

  agunapal

  committed
  2d6f60d

Commits on Sep 10, 2024

• Merge branch 'master' into feature/trt_llm_lora

  mreso

  authored
  e7a0275

Commits on Sep 13, 2024

• Using the API that supports async generate

  agunapal

  committed
  f4da9b6

• Review comments

  agunapal

  committed
  bcc036b

• Apply suggestions from code review

  Show description for cfc687d
  

  agunapal

  and

  mreso

  authored
  cfc687d

• addressed review comments

  agunapal

  committed
  f36f6a8

• Merge branch 'feature/trt_llm_lora' of https://github.com/pytorch/serve into feature/trt_llm_lora

  agunapal

  committed
  457f451

Commits on Sep 14, 2024

• Addressed review comments

  agunapal

  committed
  cc71d93

• Merge branch 'master' into feature/trt_llm_lora

  agunapal

  authored
  bbbaf69

Commits on Sep 17, 2024

• Updated the async logic based on review comments

  agunapal

  committed
  c986c7b

• Merge branch 'feature/trt_llm_lora' of https://github.com/pytorch/serve into feature/trt_llm_lora

  agunapal

  committed
  30b92c6

• Made max_batch_size and kv_cache size configurable for the launcher

  agunapal

  committed
  26a1532

• fixing lint

  agunapal

  committed
  8260619

• Merge branch 'master' into feature/trt_llm_lora

  agunapal

  authored
  589130d