Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 01:05:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/cann.Dockerfile
#	.devops/cpu.Dockerfile
#	.devops/cuda.Dockerfile
#	.devops/intel.Dockerfile
#	.devops/musa.Dockerfile
#	.devops/openvino.Dockerfile
#	.devops/rocm.Dockerfile
#	.devops/s390x.Dockerfile
#	.devops/vulkan.Dockerfile
#	.devops/zendnn.Dockerfile
#	.github/workflows/build-cache.yml
#	.github/workflows/build-openvino.yml
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/release.yml
#	app/llama.cpp
#	build-xcframework.sh
#	docs/backend/OPENVINO.md
#	ggml/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-openvino/ggml-decoder.cpp
#	ggml/src/ggml-openvino/openvino/op/add_id.cpp
#	ggml/src/ggml-openvino/openvino/op/glu_swiglu.cpp
#	ggml/src/ggml-openvino/openvino/op/mul_mat_id.cpp
#	ggml/src/ggml-openvino/openvino/op/softmax.cpp
#	ggml/src/ggml-openvino/openvino/op_table.cpp
#	ggml/src/ggml-openvino/openvino/op_table.h
#	ggml/src/ggml-sycl/softmax.cpp
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp
#	tests/test-quantize-fns.cpp
#	tools/server/CMakeLists.txt
#	tools/ui/src/lib/services/chat.service.ts
This commit is contained in:
Concedo
2026-06-27 10:33:29 +08:00
parent 4e43c21e58 050ee92d04
commit e27861e14e
54 changed files with 2681 additions and 335 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/models/mamba-base.cpp
-1
View File
@@ -169,7 +169,6 @@ ggml_tensor * llm_build_mamba_base::build_mamba2_layer(llm_graph_input_rs * inp,
GGML_ASSERT(ubatch.equal_seqs());
GGML_ASSERT(ubatch.n_tokens == n_seq_tokens * n_seqs);
GGML_ASSERT(d_inner % n_head == 0);
GGML_ASSERT(d_inner % d_state == 0);
GGML_ASSERT(d_inner % n_group == 0);
ggml_tensor * conv_states_all = mctx_cur->get_r_l(il);
src/models/mamba2.cpp
+7 -6
View File
@@ -39,10 +39,11 @@ void llama_model_mamba2::load_arch_tensors(llama_model_loader &) {
const int64_t d_inner = hparams.ssm_d_inner;
const int64_t d_state = hparams.ssm_d_state;
const int64_t n_group = hparams.ssm_n_group;
const int64_t d_in_proj = 2*d_inner + 2*n_group*d_state + n_head;
const int64_t dt_rank = hparams.ssm_dt_rank;
const int64_t conv_dim = d_inner + 2 * n_group * d_state;
const int64_t d_in_proj = d_inner + conv_dim + dt_rank;
// only an expansion factor of 2 is supported for now
GGML_ASSERT(2 * n_embd == d_inner);
tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);
@@ -68,11 +69,11 @@ void llama_model_mamba2::load_arch_tensors(llama_model_loader &) {
layer.ssm_conv1d = create_tensor(tn(LLM_TENSOR_SSM_CONV1D, "weight", i), {d_conv, d_inner + 2*n_group*d_state}, 0);
layer.ssm_conv1d_b = create_tensor(tn(LLM_TENSOR_SSM_CONV1D, "bias", i), {d_inner + 2*n_group*d_state}, 0);
layer.ssm_dt_b = create_tensor(tn(LLM_TENSOR_SSM_DT, "bias", i), {n_head}, 0);
layer.ssm_dt_b = create_tensor(tn(LLM_TENSOR_SSM_DT, "bias", i), {dt_rank}, 0);
// no "weight" suffix for these
layer.ssm_a = create_tensor(tn(LLM_TENSOR_SSM_A, i), {1, n_head}, 0);
layer.ssm_d = create_tensor(tn(LLM_TENSOR_SSM_D, i), {1, n_head}, 0);
layer.ssm_a = create_tensor(tn(LLM_TENSOR_SSM_A, i), {1, dt_rank}, 0);
layer.ssm_d = create_tensor(tn(LLM_TENSOR_SSM_D, i), {1, dt_rank}, 0);
layer.ssm_norm = create_tensor(tn(LLM_TENSOR_SSM_NORM, "weight", i), {d_inner / n_group, n_group}, 0);