Skip to content
GitLab
Explore
Sign in
Overview
Active
Stale
All
This project is mirrored from
https://github.com/ggerganov/llama.cpp
. Pull mirroring updated
Sep 19, 2024
.
opencl-extra
2d631443
·
ggml-opencl : store GPU buffer in ggml_tensor::extra
·
Sep 03, 2023
ik/metal_q3k
2cab21c3
·
nother small improvement for Q3_K on metal
·
Sep 03, 2023
ik/issue_2982
2d5f5d74
·
Also guard against extremely small weights
·
Sep 04, 2023
speculative-grammar
c79d130f
·
make : fix speculative build
·
Sep 04, 2023
metal-cont-bug
f3a84b2e
·
llama : better express the KV cache dependencies in the graph
·
Sep 04, 2023
build-metal-default
30ac7a41
·
gitignore : metal
·
Sep 04, 2023
ik/metal_rope
8a4b97e5
·
Parallel RoPE on metal
·
Sep 05, 2023
metal-fix-norm
2f689dee
·
metal : minor
·
Sep 07, 2023
bench-warmup
08c799a4
·
llama-bench : use two tokens in the warmup run for prompt evals
·
Sep 07, 2023
ik/fix_kernel_norm
7d6fac3f
·
Merge branch 'master' into ik/fix_kernel_norm
·
Sep 07, 2023
alloc-mmap-fix
b5b8ff9f
·
ggml-alloc : correctly check mmap return value for errors
·
Sep 08, 2023
ik/metal_pp
211d82a8
·
metal : minor (readibility)
·
Sep 11, 2023
ik/combined_attn_ops
76a0c903
·
POC: combined scale + diagonal mask infinity + soft max op
·
Sep 11, 2023
ik/metal_falcon_pp
c5da6f2c
·
Some cleanup
·
Sep 11, 2023
fix-rocm-shared-lib-build
61436803
·
Compile ggml-rocm with -fpic when building shared library
·
Sep 13, 2023
ik/quantize_faster
271785c3
·
Allow to enable/disable mmap via command line
·
Sep 14, 2023
mul-mat-pad
e7e7b114
·
llama : remove experimental stuff
·
Sep 14, 2023
fix-cmake-out-of-source-install
c2217ca2
·
Fix llama.h location when built outside of root directory
·
Sep 14, 2023
support-starcoder-fix
92a4f868
·
llama : make starcoder graph build more consistent with others
·
Sep 15, 2023
metal-fix-soft-max
3e15ea9b
·
metal : fix bug in soft_max kernels (out-of-bounds access)
·
Sep 15, 2023
Prev
1
…
4
5
6
7
8
9
10
11
12
…
26
Next