text-generation-inference/backends/trtllm/tests/test_backend.cpp
Funtowicz Morgan 17367438f3
Give TensorRT-LLMa proper CI/CD 😍 (#2886)
* test(ctest) enable address sanitizer

* feat(trtllm): expose finish reason to Rust

* feat(trtllm): fix logits retrieval

* misc(ci): enabe building tensorrt-llm

* misc(ci): update Rust action toolchain

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

# Conflicts:
#	Dockerfile_trtllm

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

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

* misc(ci): let's try this way

* misc(ci): again

* misc(ci): again

* misc(ci): add debug profile

* misc(ci): add debug profile

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

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

* misc(ci): WAT

* misc(ci): WAT

* misc(ci): WAT

* misc(ci): WAT

* misc(ci): WAT

* misc(backend): test with TGI S3 conf

* misc(backend): test with TGI S3 conf

* misc(backend): once more?

* misc(backend): let's try with GHA

* misc(backend): missing env directive

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

* misc(backend): ok let's debug smtg

* misc(backend): WWWWWWWWWWWWWAAAAAAAA

* misc(backend): kthxbye retry s3

* misc(backend): use session token

* misc(backend): add more info

* misc(backend): lets try 1h30

* misc(backend): lets try 1h30

* misc(backend): increase to 2h

* misc(backend): lets try...

* misc(backend): lets try...

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

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

* misc(backend): add some tags

* misc(backend): disable Werror for now

* misc(backend): added automatic gha detection

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

* misc(backend): forward env

* misc(backend): forward env

* misc(backend): let's try

* misc(backend): let's try

* misc(backend): again

* misc(backend): again

* misc(backend): again

* misc(backend): again

* misc(backend): again

* misc(backend): fix sscache -> sccache

* misc(backend): fix sscache -> sccache

* misc(backend): fix sscache -> sccache

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

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

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

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

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

* change runner size

* fix: Correctly tag docker images (#2878)

* fix: Correctly tag docker images

* fix: Correctly tag docker images

* misc(llamacpp): maybe?

* misc(llamacpp): maybe?

* misc(llamacpp): maybe?

* misc(ci): gogogo

* misc(ci): gogogo

* misc(ci): gogogo

* misc(ci): gogogo

* misc(ci): gogogo

* misc(ci): gogogo

* misc(ci): go

* misc(ci): go

* misc(ci): go

* misc(ci): use bin folder

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

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

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

* misc(ci): give the wf a name

* Create test-trtllm.yml

* Update test-trtllm.yml

* Create build-trtllm2

* Rename build-trtllm2 to 1-build-trtllm2

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

* misc(ci): fw secrets

* Update 1-test-trtllm2.yml

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

* Update 1-test-trtllm2.yml

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

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

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

* misc(ci): rights?

* misc(ci): rights?

* misc(ci): once more?

* misc(ci): once more?

* misc(ci): baby more time?

* misc(ci): baby more time?

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

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

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

* misc(ci): install tensorrt_llm_executor_static

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

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

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

* misc(ci): reintroduce variables

* misc(ci): enforce sccache

* misc(ci): correct right job name dependency

* misc(ci): detect dev profile for debug

* misc(ci): detect gha build

* misc(ci): detect gha build

* misc(ci): ok debug

* misc(ci): wtf

* misc(ci): wtf2

* misc(ci): wtf3

* misc(ci): use commit HEAD instead of merge commit for image id

* misc(ci): wtfinfini

* misc(ci): wtfinfini

* misc(ci): KAMEHAMEHA

* Merge TRTLLM in standard CI

* misc(ci): remove input machine

* misc(ci): missing id-token for AWS auth

* misc(ci): missing id-token for AWS auth

* misc(ci): missing id-token for AWS auth

* misc(ci): again...

* misc(ci): again...

* misc(ci): again...

* misc(ci): again...

* misc(ci): missing benchmark

* misc(ci): missing backends

* misc(ci): missing launcher

* misc(ci): give everything aws needs

* misc(ci): give everything aws needs

* misc(ci): fix warnings

* misc(ci): attempt to fix sccache not building trtllm

* misc(ci): attempt to fix sccache not building trtllm again

---------

Co-authored-by: Guillaume LEGENDRE <glegendre01@gmail.com>
Co-authored-by: Hugo Larcher <hugo.larcher@huggingface.co>
Co-authored-by: Pauline Bailly-Masson <155966238+paulinebm@users.noreply.github.com>
2025-01-21 10:19:16 +01:00

155 lines
6.2 KiB
C++

//
// Created by mfuntowicz on 12/3/24.
//
#include <catch2/catch_all.hpp>
#include <nlohmann/json.hpp>
#include <tensorrt_llm/executor/executor.h>
#include "backend.hpp"
using namespace huggingface::tgi::backends::trtllm;
TEST_CASE("parse generation_config.json all set", "[generation_config_t]")
{
const json config_j = {{"temperature", 0.6},
{"top_p", 0.95},
{"eos_token_id", {1, 2, 3}}};
const auto generation_config = generation_config_t(config_j);
REQUIRE_THAT(generation_config.temperature, Catch::Matchers::WithinAbs(0.6, 1e-6));
REQUIRE_THAT(generation_config.top_p, Catch::Matchers::WithinAbs(0.95, 1e-6));
// Stop words
REQUIRE_FALSE(generation_config.stop_words.empty());
REQUIRE(generation_config.stop_words.size() == config_j["/eos_token_id"_json_pointer].size());
for (auto [lhs, rhs]: std::views::zip(generation_config.stop_words, std::list<std::vector<int32_t>>{{1},
{2},
{3}})) {
// Currently we do not support multi-tokens stop words
REQUIRE(lhs.size() == 1);
REQUIRE(rhs.size() == 1);
REQUIRE_THAT(lhs, Catch::Matchers::UnorderedEquals(rhs));
}
}
TEST_CASE("parse generation_config.json default", "[generation_config_t]")
{
const json config_j = {{"eos_token_id", {1, 2, 3}}};
const auto generation_config = generation_config_t(config_j);
REQUIRE_THAT(generation_config.temperature, Catch::Matchers::WithinAbs(1.0, 1e-6));
REQUIRE_THAT(generation_config.top_p, Catch::Matchers::WithinAbs(1.0, 1e-6));
REQUIRE_FALSE(generation_config.stop_words.empty());
REQUIRE(generation_config.stop_words.size() == config_j["/eos_token_id"_json_pointer].size());
for (auto [lhs, rhs]: std::views::zip(generation_config.stop_words, std::list<std::vector<int32_t>>{{1},
{2},
{3}})) {
// Currently we do not support multi-tokens stop words
REQUIRE(lhs.size() == 1);
REQUIRE(rhs.size() == 1);
REQUIRE_THAT(lhs, Catch::Matchers::UnorderedEquals(rhs));
}
}
TEST_CASE("parse generation_config.json empty", "[generation_config_t]")
{
const json config_j = {{"eos_token_id", {}}};
const auto generation_config = generation_config_t(config_j);
REQUIRE_THAT(generation_config.temperature, Catch::Matchers::WithinAbs(1.0, 1e-6));
REQUIRE_THAT(generation_config.top_p, Catch::Matchers::WithinAbs(1.0, 1e-6));
REQUIRE(generation_config.stop_words.empty());
const json config_j2 = {};
const auto generation_config2 = generation_config_t(config_j);
REQUIRE_THAT(generation_config2.temperature, Catch::Matchers::WithinAbs(1.0, 1e-6));
REQUIRE_THAT(generation_config2.top_p, Catch::Matchers::WithinAbs(1.0, 1e-6));
REQUIRE(generation_config2.stop_words.empty());
}
TEST_CASE("parallel_config single", "[backend_workspace_t]")
{
// Generate temporary folder
const auto tmp_p = std::filesystem::temp_directory_path();
const auto config_p = tmp_p / "config.json";
const auto generation_config_p = tmp_p / "generation_config.json";
// Generate content
std::ofstream o_config(config_p);
o_config << R"({"pretrained_config": {"mapping": {"world_size": 2}}})"_json;
o_config.close();
std::ofstream o_generation_config(generation_config_p);
o_generation_config << R"({"eos_token_id": []})"_json;
o_generation_config.close();
const auto workspace = backend_workspace_t(tmp_p.generic_string(), tmp_p.generic_string());
const auto parallel = workspace.parallel_config();
REQUIRE(parallel.getCommunicationMode() == tle::CommunicationMode::kORCHESTRATOR);
REQUIRE(parallel.getCommunicationType() == tle::CommunicationType::kMPI);
std::filesystem::remove(config_p);
std::filesystem::remove(generation_config_p);
}
TEST_CASE("parallel_config multi", "[backend_workspace_t]")
{
// Generate temporary folder
const auto tmp_p = std::filesystem::temp_directory_path();
const auto config_p = tmp_p / "config.json";
const auto generation_config_p = tmp_p / "generation_config.json";
// Generate content
std::ofstream o_config(config_p);
o_config << R"({"pretrained_config": {"mapping": {"world_size": 1}}})"_json;
o_config.close();
std::ofstream o_generation_config(generation_config_p);
o_generation_config << R"({"eos_token_id": []})"_json;
o_generation_config.close();
const auto workspace = backend_workspace_t(tmp_p.generic_string(), tmp_p.generic_string());
const auto parallel = workspace.parallel_config();
REQUIRE(parallel.getCommunicationMode() == tle::CommunicationMode::kLEADER);
REQUIRE(parallel.getCommunicationType() == tle::CommunicationType::kMPI);
std::filesystem::remove(config_p);
std::filesystem::remove(generation_config_p);
}
TEST_CASE("executor_config", "[backend_workspace_t]")
{
}
TEST_CASE("sampling_params_t to tle::SamplingConfig", "[backend_t]")
{
const sampling_params_t params = {40, 0.95, 0.9, 1.0, 0.6, 2014};
const auto config = static_cast<tle::SamplingConfig>(params);
REQUIRE(config.getTopK().has_value());
REQUIRE(config.getTopK().value() == params.top_k);
REQUIRE(config.getSeed().has_value());
REQUIRE(config.getSeed().value() == params.seed);
REQUIRE(config.getTopP().has_value());
REQUIRE_THAT(*config.getTopP(), Catch::Matchers::WithinAbs(params.top_p, 1e-6f));
REQUIRE(config.getRepetitionPenalty().has_value());
REQUIRE_THAT(*config.getRepetitionPenalty(), Catch::Matchers::WithinAbs(params.repetition_penalty, 1e-6f));
REQUIRE(config.getFrequencyPenalty().has_value());
REQUIRE_THAT(*config.getFrequencyPenalty(), Catch::Matchers::WithinAbs(params.frequency_penalty, 1e-6f));
REQUIRE(config.getTemperature().has_value());
REQUIRE_THAT(*config.getTemperature(), Catch::Matchers::WithinAbs(params.temperature, 1e-6f));
}