vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

RoPE: fix back, CUDA support for back + noncont. (#11240)

Browse source 
* RoPE: fix back, CUDA support for back + noncont.

* fix comments reg. non-cont. RoPE support [no-ci]
This commit is contained in:
Johannes Gäßler 2025-01-15 12:51:37 +01:00 • committed by GitHub
parent 0ccd7f3eb2
commit 432df2d5f9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 269 additions and 258 deletions
Download patch file Download diff file Expand all files Collapse all files

8
src/llama.cpp
View file

@ -4642,7 +4642,7 @@ struct llm_build_context {
0);
cb(v_states, "v_states", il);
q_pe = ggml_cont(ctx0, q_pe); // TODO: the CUDA backend does not support non-contiguous RoPE
q_pe = ggml_cont(ctx0, q_pe); // TODO: the CUDA backend used to not support non-cont. RoPE, investigate removing this
q_pe = ggml_rope_ext(
ctx0, q_pe, inp_pos, rope_factors,
n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
@ -4651,7 +4651,7 @@ struct llm_build_context {
cb(q_pe, "q_pe", il);
// shared RoPE key
k_pe = ggml_cont(ctx0, k_pe); // TODO: the CUDA backend does not support non-contiguous RoPE
k_pe = ggml_cont(ctx0, k_pe); // TODO: the CUDA backend used to not support non-cont. RoPE, investigate removing this
k_pe = ggml_rope_ext(
ctx0, k_pe, inp_pos, rope_factors,
n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
@ -6496,7 +6496,7 @@ struct llm_build_context {
0);
cb(v_states, "v_states", il);
q_pe = ggml_cont(ctx0, q_pe); // TODO: the CUDA backend does not support non-contiguous RoPE
q_pe = ggml_cont(ctx0, q_pe); // TODO: the CUDA backend used to not support non-cont. RoPE, investigate removing this
q_pe = ggml_rope_ext(
ctx0, q_pe, inp_pos, nullptr,
n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
@ -6505,7 +6505,7 @@ struct llm_build_context {
cb(q_pe, "q_pe", il);
// shared RoPE key
k_pe = ggml_cont(ctx0, k_pe); // TODO: the CUDA backend does not support non-contiguous RoPE
k_pe = ggml_cont(ctx0, k_pe); // TODO: the CUDA backend used to not support non-cont. RoPE, investigate removing this
k_pe = ggml_rope_ext(
ctx0, k_pe, inp_pos, nullptr,
n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,