Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

(ffi) cleanup again

This commit is contained in:
Morgan Funtowicz 2024-08-02 22:17:02 +00:00 committed by Morgan Funtowicz
parent f4a74be384
commit 2883c042ed
2 changed files with 0 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
backends/trtllm/include/ffi.h
View File

@ -14,11 +14,8 @@ namespace huggingface::tgi::backends {
#include "backends/trtllm/src/lib.rs.h"
namespace huggingface::tgi::backends {
// struct GenerationContext;
class TensorRtLlmBackendImpl : public TensorRtLlmBackend {
public:
/***
@ -28,12 +25,6 @@ namespace huggingface::tgi::backends {
*/
TensorRtLlmBackendImpl(const std::string_view &engineFolder, const std::string_view &executorWorker);
/***
*
* @return
*/
bool IsReady() const;
/***
*
* @param tokens

4
backends/trtllm/src/ffi.cpp
View File

@ -20,10 +20,6 @@ huggingface::tgi::backends::TensorRtLlmBackendImpl::TensorRtLlmBackendImpl(
) : TensorRtLlmBackend(engineFolder, executorWorker) {}
bool huggingface::tgi::backends::TensorRtLlmBackendImpl::IsReady() const {
return TensorRtLlmBackend::IsReady();
}
uint64_t huggingface::tgi::backends::TensorRtLlmBackendImpl::Submit(
rust::Slice<const uint32_t> tokens, uint32_t maxNewTokens,
int32_t topK, float_t topP, float_t temperature,