kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-13 22:18:36 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

perf: customize cublastLt algo for Llamba 3.3 70B TP4 (#6315)

Browse Source 
Signed-off-by: Zhenhua Wang <zhenhuaw@nvidia.com>
This commit is contained in:
Zhenhua Wang 2025-07-24 23:01:15 +08:00 committed by GitHub
parent 7b6aadc800
commit 62298bc473
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.clangd
View File

@ -29,7 +29,7 @@ CompileFlags:
# Tweak the clangd parse settings for all files
CompileFlags:
Compiler: clang++
CompilationDatabase: .
CompilationDatabase: cpp/build
Add:
# report all errors
- "-ferror-limit=0"

3
cpp/tensorrt_llm/thop/cublasScaledMM.cpp
View File

@ -66,6 +66,9 @@ AlgoListType fp8_algo_list = {
{{8, 8192, 8192}, {393, 36, 1, 0, 0, 5, 2}},
// [-algo66 -m_tile10 -m_stages36 -m_numsK1 -m_reduction0 -m_swizzle0 -m_custom1 -m_mma0 -m_cga2 -m_scheduling1]
{{8, 8192, 57344}, {10, 36, 1, 0, 0, 1, 2}},
// Llama-3.3-70B TP4 (this is the default algo on B200. Here we aim to use the same algo on GB200.)
// [-algo66 -m_tile393 -m_stages36 -m_numsK1 -m_reduction0 -m_swizzle0 -m_custom1 -m_mma0 -m_cga4 -m_scheduling1]
{{8, 8192, 14336}, {393, 36, 1, 0, 1, 1, 4}},
};
void set_algo_attr(cublasLtMatmulAlgo_t& algo, std::array<int, 7> const& attr_list)