LLM-Inference/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-12 22:31:11 +04:00
Code Issues Packages Projects Releases Wiki Activity
10,397 Commits 684 Branches 7,066 Tags
master
Commit Graph
3 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Rafail GiavrimisandGitHub ebb546b7e9 CUDA: only disable CUDA graphs when mul_mat_id actually needs a stream sync (#26802) 2026-08-11 20:50:03 +03:00
Rafail GiavrimisandGitHub 687e778927 CUDA: fuse rms_norm + mul + rope (+ view + set_rows) (#26767) 
* CUDA: fuse rms_norm + mul + rope (+ view + set_rows)

* tests: add broadcast weight case to rms_norm_mul_rope

* CUDA: check memory ranges before rms_norm rope fusion

* CUDA: check memory ranges in rope set_rows fusion
 2026-08-09 00:32:37 +08:00
Rafail GiavrimisandGitHub 69bf643791 CUDA: fix thread/block count in quantized cpy kernel launches (#26731) 
* CUDA: fix thread/block count in quantized cpy kernel launches

* tests: add uneven block count cpy case
 2026-08-08 07:40:04 +03:00