thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

docs : Minor cleanups (#19252)

Browse source 
* Update old URLs to github.com/ggml-org/

* Bump copyrights
This commit is contained in:
Christian Kastner 2026-02-02 07:38:55 +01:00 • committed by GitHub
parent b4d05a3d2f
commit 7a4ca3cbd9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
36 changed files with 42 additions and 42 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/models/deepseek2.cpp
View file

@ -14,7 +14,7 @@ llm_build_deepseek2::llm_build_deepseek2(const llama_model & model, const llm_gr
const uint32_t kv_lora_rank = hparams.n_lora_kv;
// We have to pre-scale kq_scale and attn_factor to make the YaRN RoPE work correctly.
// See https://github.com/ggerganov/llama.cpp/discussions/7416 for detailed explanation.
// See https://github.com/ggml-org/llama.cpp/discussions/7416 for detailed explanation.
// And also: https://github.com/ggml-org/llama.cpp/pull/17945 [TAG_DEEPSEEK2_YARN_LOG_MUL_FIX]
// first cancel the adjustment from llama_hparams::yarn_attn_factor_adjust to get the original attn_factor