nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 24 Packages Projects Releases Wiki Activity
5,318 Commits 1 Branch 0 Tags
15e03282bb432631193464100c2237a3b6bcfe4c
Commit Graph
3 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
SXXandGitHub 77d5e9a76a ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs (#13107) 
* ggml: dynamic x86_64 feature detection for FP32 <-> FP16/BF16 conversion

* move fp converter to ggml-cpu

* Switch ggml_compute_forward_get_rows_f16/bf16 to new ggml_cpu_fp16/bf16_to_fp32
 2025-04-26 16:05:31 +02:00
SXXandGitHub e959d32b1c ggml: use _mm[512/256]_dpbusd[_avx]_epi32 to directly accumulate into the result register (#12773) 
* ggml: use _mm[512/256]_dpbusd[_avx]_epi32 to directly accumulate into the result register

* simplifies the codebase by removing redundant functions
 2025-04-14 08:47:55 +03:00
SXXandGitHub 5b359bb1e3 ggml: fix zero division in ‘dne’ calculation in CUDA COUNT_EQUAL operator when ‘ne’ is small (#10213) 2024-11-09 08:35:46 +01:00