 slaren
|
d232aca5a7
llama : initial ggml-backend integration (#4520)
|
2 years ago |
 Ebey Abraham
|
b9e74f9bca
llama : add phi-2 + fix NeoX rope + ggml_mul_mat_set_prec (#4490)
|
2 years ago |
|
slaren
|
ee4725a686
ggml : group mul_mat_id rows by matrix (cpu only) (#4480)
|
2 years ago |
|
slaren
|
6744dbe924
ggml : use ggml_row_size where possible (#4472)
|
2 years ago |
|
slaren
|
cafcd4f895
ggml : remove n_dims from ggml_tensor (#4469)
|
2 years ago |
 LostRuins
|
20a68a7030
ggml : add ggml_row_size() (fixes llama out of space) (#4461)
|
2 years ago |
 Georgi Gerganov
|
55e87c3749
ggml : fix OpenCL broadcast requirement for ggml_mul (close #4453)
|
2 years ago |
|
Georgi Gerganov
|
4d98d9a656
sync : ggml (SD ops, tests, kernels) (#4444)
|
2 years ago |
|
slaren
|
799a1cb13b
llama : add Mixtral support (#4406)
|
2 years ago |
 Richard Kiss
|
9494d7c477
english : use `typos` to fix comments and logs (#4354)
|
2 years ago |
|
Georgi Gerganov
|
fe680e3d10
sync : ggml (new ops, tests, backend, etc.) (#4359)
|
2 years ago |
|
Georgi Gerganov
|
fbbc42827b
ggml : reuse ggml_get_n_tasks() in ggml_graph_plan() (#4308)
|
2 years ago |
|
Georgi Gerganov
|
adf3de4f69
ggml : fix soft max out-of-bounds access (#4307)
|
2 years ago |
|
Georgi Gerganov
|
ef47ec18da
ggml : add ggml_soft_max_ext (#4256)
|
2 years ago |
|
Georgi Gerganov
|
8406b0924b
ggml : re-enable BLAS for CPU when src0 != F32 + remove redundant full offload checks in llama.cpp (#4240)
|
2 years ago |
 Jared Van Bortel
|
f3b269813f
ggml : fix -Warray-bounds warning with gcc (#4231)
|
2 years ago |
|
slaren
|
e85bb1a8e7
llama : add functions to get the model's metadata (#4013)
|
2 years ago |
 gwjr
|
3e916a07ac
finetune : speed-up ggml_compute_forward_out_prod_f32 via BLAS (#4079)
|
2 years ago |
 texmex76
|
8da46278e1
gguf : fix potential infinite loops while parsing (#4100)
|
2 years ago |
|
Georgi Gerganov
|
3d68f364f1
ggml : sync (im2col, GPU conv, 32-bit arm compat) (#4060)
|
2 years ago |
|
Georgi Gerganov
|
4760e7cc0b
sync : ggml (backend v2) (#3912)
|
2 years ago |
 xaedes
|
e9c1cecb9d
ggml : fix backward rope after YaRN (#3974)
|
2 years ago |
|
Georgi Gerganov
|
4ff1046d75
gguf : print error for GGUFv1 files (#3908)
|
2 years ago |
|
Georgi Gerganov
|
2756c4fbff
gguf : remove special-case code for GGUFv1 (#3901)
|
2 years ago |
 cebtenzzre
|
898aeca90a
llama : implement YaRN RoPE scaling (#2268)
|
2 years ago |
 Andrew Godfrey
|
73bdcb395e
finetune : add -ngl parameter (#3762)
|
2 years ago |
|
Georgi Gerganov
|
207b51900e
ggml : move FP16 <-> FP32 code to ggml-impl.h (#3861)
|
2 years ago |
|
Georgi Gerganov
|
d69d777c02
ggml : quantization refactoring (#3833)
|
2 years ago |
|
Georgi Gerganov
|
b2f7e04bd3
sync : ggml (conv ops + cuda MSVC fixes) (#3765)
|
2 years ago |
|
Georgi Gerganov
|
2b4ea35e56
cuda : add batched cuBLAS GEMM for faster attention (#3749)
|
2 years ago |
