Code

Give TensorRT-LLMa proper CI/CD 😍#2886

Code

Open

mfuntowicz wants to merge 107 commits intomainhuggingface/text-generation-inference:mainfrom trtllm/cihuggingface/text-generation-inference:trtllm/ciCopy head branch name to clipboard

+638-168

Commits

Commits on Jan 7, 2025

• test(ctest) enable address sanitizer

  mfuntowicz

  committed
  d4a8a1a

• feat(trtllm): expose finish reason to Rust

  mfuntowicz

  committed
  235080c

• feat(trtllm): fix logits retrieval

  mfuntowicz

  committed
  994fa52

• misc(ci): enabe building tensorrt-llm

  mfuntowicz

  committed
  78434e6

• misc(ci): update Rust action toolchain

  mfuntowicz

  committed
  2f61ec4

• misc(ci): let's try to build the Dockerfile for trtllm

  mfuntowicz

  committed
  0ff0c6a

• misc(ci): provide mecanism to cache inside container

  mfuntowicz

  committed
  01a5fc1

• misc(ci): export aws creds as output of step

  mfuntowicz

  committed
  5f95074

• misc(ci): let's try this way

  mfuntowicz

  committed
  497fbc1

• misc(ci): again

  mfuntowicz

  committed
  4fd26ca

• misc(ci): again

  mfuntowicz

  committed
  e73234f

• misc(ci): add debug profile

  mfuntowicz

  committed
  522a992

• misc(ci): add debug profile

  mfuntowicz

  committed
  f0bf952

• misc(ci): lets actually use sccache ...

  mfuntowicz

  committed
  85e924e

• misc(ci): do not build with ssl enabled

  mfuntowicz

  committed
  28af5da

• misc(ci): WAT

  mfuntowicz

  committed
  48e6dac

• misc(ci): WAT

  mfuntowicz

  committed
  a733f42

• misc(ci): WAT

  mfuntowicz

  committed
  f32dfeb

• misc(ci): WAT

  mfuntowicz

  committed
  b927998

• misc(ci): WAT

  mfuntowicz

  committed
  3859988

• misc(backend): test with TGI S3 conf

  mfuntowicz

  committed
  de88905

• misc(backend): test with TGI S3 conf

  mfuntowicz

  committed
  fed6455

• misc(backend): once more?

  mfuntowicz

  committed
  44feeac

• misc(backend): let's try with GHA

  mfuntowicz

  committed
  0499ef7

• misc(backend): missing env directive

  mfuntowicz

  committed
  4537094

• misc(backend): make sure to correctly set IS_GHA_BUILD=true in wf

  mfuntowicz

  committed
  0501210

• misc(backend): ok let's debug smtg

  mfuntowicz

  committed
  87c0f86

• misc(backend): WWWWWWWWWWWWWAAAAAAAA

  mfuntowicz

  committed
  99e4d44

• misc(backend): kthxbye retry s3

  mfuntowicz

  committed
  1edbab6

• misc(backend): use session token

  mfuntowicz

  committed
  f8e0d84

• misc(backend): add more info

  mfuntowicz

  committed
  5e4a6bb

• misc(backend): lets try 1h30

  mfuntowicz

  committed
  fa269d5

• misc(backend): lets try 1h30

  mfuntowicz

  committed
  6bb4dbb

• misc(backend): increase to 2h

  mfuntowicz

  committed
  7d4694d

• misc(backend): lets try...

  mfuntowicz

  committed
  37aa2c6

• misc(backend): lets try...

  mfuntowicz

  committed
  39b4239

• misc(backend): let's build for ci-runtime

  mfuntowicz

  committed
  80c357a

• misc(backend): let's add some more tooling

  mfuntowicz

  committed
  5196419

• misc(backend): add some tags

  mfuntowicz

  committed
  5afd085

• misc(backend): disable Werror for now

  mfuntowicz

  committed
  18cdcdd

• misc(backend): added automatic gha detection

  mfuntowicz

  committed
  12e2c73

• misc(backend): remove leak sanitizer which is included in asan

  mfuntowicz

  committed
  76f23d5

• misc(backend): forward env

  mfuntowicz

  committed
  3b47b0e

• misc(backend): forward env

  mfuntowicz

  committed
  cf1d8ed

• misc(backend): let's try

  mfuntowicz

  committed
  5d5c288

• misc(backend): let's try

  mfuntowicz

  committed
  34f435d

• misc(backend): again

  mfuntowicz

  committed
  d0c0a3c

• misc(backend): again

  mfuntowicz

  committed
  fefafaf

• misc(backend): again

  mfuntowicz

  committed
  3f40a93

• misc(backend): again

  mfuntowicz

  committed
  0128939

• misc(backend): again

  mfuntowicz

  committed
  43ab954

• misc(backend): fix sscache -> sccache

  mfuntowicz

  committed
  447782f

• misc(backend): fix sscache -> sccache

  mfuntowicz

  committed
  b53e388

• misc(backend): fix sscache -> sccache

  mfuntowicz

  committed
  cb5ecf3

• misc(backend): let's actually cache things now

  mfuntowicz

  committed
  585b3c2

• misc(backend): let's actually cache things now

  mfuntowicz

  committed
  fb2e11e

• misc(backend): attempt to run the testS?

  mfuntowicz

  committed
  293423c

• misc(backend): attempt to run the tests?

  mfuntowicz

  committed
  a7d3dee

• misc(backend): attempt to run the tests?

  mfuntowicz

  committed
  b721421

• change runner size

  

  glegendre01

  authored and

  mfuntowicz

  committed
  7c83885

• fix: Correctly tag docker images (#2878)

  Show description for a301559
  

  Hugoch

  authored and

  mfuntowicz

  committed
  a301559

• misc(llamacpp): maybe?

  mfuntowicz

  committed
  4f87837

• misc(llamacpp): maybe?

  mfuntowicz

  committed
  3806a33

• misc(llamacpp): maybe?

  mfuntowicz

  committed
  7f50afd

• misc(ci): gogogo

  mfuntowicz

  committed
  51aefb1

• misc(ci): gogogo

  mfuntowicz

  committed
  0c972cd

• misc(ci): gogogo

  mfuntowicz

  committed
  2a6d88d

• misc(ci): gogogo

  mfuntowicz

  committed
  ccf18b3

• misc(ci): gogogo

  mfuntowicz

  committed
  1565c8c

• misc(ci): gogogo

  mfuntowicz

  committed
  d9f3a9f

• misc(ci): go

  mfuntowicz

  committed
  bd0052e

• misc(ci): go

  mfuntowicz

  committed
  7c05f22

• misc(ci): go

  mfuntowicz

  committed
  99e226a

• misc(ci): use bin folder

  mfuntowicz

  committed
  541618e

• misc(ci): make the wf callable for reuse

  mfuntowicz

  committed
  50de9ed

• misc(ci): make the wf callable for reuse (bis)

  mfuntowicz

  committed
  40d299f

• misc(ci): make the wf callable for reuse (bis)

  mfuntowicz

  committed
  5bc1245

• misc(ci): give the wf a name

  mfuntowicz

  committed
  ccafee0

• Create test-trtllm.yml

  paulinebm

  authored
  b65b9b5

• Update test-trtllm.yml

  paulinebm

  authored
  38401a9

• Create build-trtllm2

  paulinebm

  authored
  0eeedbe

• Rename build-trtllm2 to 1-build-trtllm2

  paulinebm

  authored
  64b4265

• Rename test-trtllm.yml to 1-test-trtllm2.yml

  paulinebm

  authored
  4ed9938

• misc(ci): fw secrets

  mfuntowicz

  committed
  f84891e

• Update 1-test-trtllm2.yml

  paulinebm

  authored
  66d6611

• Rename 1-build-trtllm2 to 1-build-trtllm2.yml

  paulinebm

  authored
  de72dae

• Update 1-test-trtllm2.yml

  paulinebm

  authored
  7b1f4bc

• misc(ci): use ci-build.yaml as main dispatcher

  mfuntowicz

  committed
  8d22a96

• Delete .github/workflows/1-test-trtllm2.yml

  paulinebm

  authored
  1d21d34

• Delete .github/workflows/1-build-trtllm2.yml

  paulinebm

  authored
  fde696a

• misc(ci): rights?

  mfuntowicz

  committed
  2894cbc

• misc(ci): rights?

  mfuntowicz

  committed
  ca7099c

• misc(ci): once more?

  mfuntowicz

  committed
  f9ebcd9

• misc(ci): once more?

  mfuntowicz

  committed
  6309957

• misc(ci): baby more time?

  mfuntowicz

  committed
  5fb03ae

• misc(ci): baby more time?

  mfuntowicz

  committed
  a0e8c87

Commits on Jan 8, 2025

• misc(ci): try the permission above again?

  mfuntowicz

  committed
  5126275

• misc(ci): try the permission above again?

  mfuntowicz

  committed
  7ce285d

• misc(ci): try the permission scoped again?

  mfuntowicz

  committed
  f1f152c

• misc(ci): install tensorrt_llm_executor_static

  mfuntowicz

  committed
  65ab495

• misc(ci): attempt to rebuild with sccache?

  mfuntowicz

  committed
  d7698e8

• misc(ci):run the tests on GPU instance

  mfuntowicz

  committed
  c4abc20

• misc(ci): let's actually setup sccache in the build.rs

  mfuntowicz

  committed
  1a95ee4

Commits on Jan 9, 2025

• misc(ci): reintroduce variables

  mfuntowicz

  committed
  59db9fe

• misc(ci): enforce sccache

  mfuntowicz

  committed
  cf846aa

• misc(ci): correct right job name dependency

  mfuntowicz

  committed
  6aadb79

• misc(ci): detect dev profile for debug

  mfuntowicz

  committed
  dbe80ea