Runtime Coordinator#

class RuntimeCoordinator#

Owns local LLM rank workers and communication groups for a runtime coordinator.

Public Functions

explicit RuntimeCoordinator(Config config)#
~RuntimeCoordinator()#
RuntimeCoordinator(RuntimeCoordinator const&) = delete#
RuntimeCoordinator &operator=(RuntimeCoordinator const&) = delete#
RuntimeCoordinator(RuntimeCoordinator&&) = delete#
RuntimeCoordinator &operator=(RuntimeCoordinator&&) = delete#
bool captureDecodingCUDAGraph(cudaStream_t stream = nullptr)#
bool dispatchRequest(
LLMGenerationRequest const &request,
bool enableProfiling,
bool outputThinkerEmbeddings = false,
cudaStream_t stream = nullptr
)#
bool genAndSaveSystemPromptKVCache(
std::string const &prompt,
std::string const &loraWeightsName,
cudaStream_t stream = nullptr
)#
void setVisualPrunerConfig(VisualPrunerConfig const &config)#
LLMGenerationResponse takeRankResponse(int32_t globalRank)#
LLMRankRuntime &rootRuntime()#
LLMRankRuntime const &rootRuntime() const#
bool ownsGlobalRank(int32_t globalRank) const noexcept#
bool localRanksSucceeded() const noexcept#
struct Config#

Public Members

std::string engineDir#
std::string multimodalEngineDir#
std::unordered_map<std::string, std::string> loraWeightsMap#
ParallelConfig parallelConfig#
std::optional<SpecDecodeDraftingConfig> draftingConfig#
ContextCacheConfig contextCacheConfig#
std::string checkpointDir#
std::string draftCheckpointDir#
std::vector<int32_t> localRanks#
std::unordered_map<int32_t, int32_t> localRankDevices#
std::vector<cudaStream_t> localStreams#
bool ownsLocalStreams = {true}#
std::vector<ParallelBackendHandles> backendHandles#
std::unique_ptr<ModelArtifacts> modelArtifacts#
struct Config

Public Members

std::string engineDir
std::string multimodalEngineDir
std::unordered_map<std::string, std::string> loraWeightsMap
ParallelConfig parallelConfig
std::optional<SpecDecodeDraftingConfig> draftingConfig
ContextCacheConfig contextCacheConfig
std::string checkpointDir
std::string draftCheckpointDir
std::vector<int32_t> localRanks
std::unordered_map<int32_t, int32_t> localRankDevices
std::vector<cudaStream_t> localStreams
bool ownsLocalStreams = {true}
std::vector<ParallelBackendHandles> backendHandles
std::unique_ptr<ModelArtifacts> modelArtifacts