mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2025-09-11 01:24:36 +00:00
Merge branch 'upstream' into concedo_experimental
# Conflicts: # .github/workflows/build.yml # CMakeLists.txt # cmake/common.cmake # docs/backend/SYCL.md # examples/main/README.md # examples/speculative/speculative.cpp # ggml/CMakeLists.txt # ggml/src/CMakeLists.txt # ggml/src/ggml-cpu/CMakeLists.txt # ggml/src/ggml-musa/CMakeLists.txt # ggml/src/ggml-sycl/CMakeLists.txt # ggml/src/ggml-vulkan/vulkan-shaders/CMakeLists.txt # tests/test-backend-ops.cpp
This commit is contained in:
commit
0c90d2ebcf
58 changed files with 4222 additions and 1537 deletions
|
@ -759,10 +759,19 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
|
|||
// NOTE: can't use LLM_TN here because the layer number is not known
|
||||
quantize &= name.find("ssm_conv1d.weight") == std::string::npos;
|
||||
|
||||
// do not quantize RWKV's time_mix_first tensors
|
||||
// do not quantize RWKV's small yet 2D weights
|
||||
quantize &= name.find("time_mix_first.weight") == std::string::npos;
|
||||
quantize &= name.find("time_mix_w0.weight") == std::string::npos;
|
||||
quantize &= name.find("time_mix_w1.weight") == std::string::npos;
|
||||
quantize &= name.find("time_mix_w2.weight") == std::string::npos;
|
||||
quantize &= name.find("time_mix_v0.weight") == std::string::npos;
|
||||
quantize &= name.find("time_mix_v1.weight") == std::string::npos;
|
||||
quantize &= name.find("time_mix_v2.weight") == std::string::npos;
|
||||
quantize &= name.find("time_mix_a0.weight") == std::string::npos;
|
||||
quantize &= name.find("time_mix_a1.weight") == std::string::npos;
|
||||
quantize &= name.find("time_mix_a2.weight") == std::string::npos;
|
||||
quantize &= name.find("time_mix_g1.weight") == std::string::npos;
|
||||
quantize &= name.find("time_mix_g2.weight") == std::string::npos;
|
||||
quantize &= name.find("time_mix_decay_w1.weight") == std::string::npos;
|
||||
quantize &= name.find("time_mix_decay_w2.weight") == std::string::npos;
|
||||
quantize &= name.find("time_mix_lerp_fused.weight") == std::string::npos;
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue