Skip to content
GitLab
Explore
Sign in
Tags
Tags give the ability to mark specific points in history as being important
b2658
ef21ce4c
·
imatrix : remove invalid assert (#6632)
·
Apr 12, 2024
b2657
dee7f8d6
·
Correct free memory and total memory. (#6630)
·
Apr 12, 2024
b2656
81da18e7
·
eval-callback: use ggml_op_desc to pretty print unary operator name (#6631)
·
Apr 12, 2024
b2655
9ed2737a
·
ci : disable Metal for macOS-latest-cmake-x64 (#6628)
·
Apr 12, 2024
b2646
b3a96f27
·
minor layout improvements (#6572)
·
Apr 10, 2024
b2645
4f407a0a
·
llama : add model types for mixtral (#6589)
·
Apr 10, 2024
b2636
5dc9dd71
·
llama : add Command R Plus support (#6491)
·
Apr 09, 2024
b2632
b73e564b
·
quantize : fix precedence of cli args (#6541)
·
Apr 08, 2024
b2630
beea6e1b
·
llama : save and restore kv cache for single seq id (#6341)
·
Apr 08, 2024
b2629
87fb5b42
·
remove row=1 cond (#6532)
·
Apr 08, 2024
b2619
54ea0698
·
sync : ggml
·
Apr 06, 2024
b2615
a8bd14d5
·
gguf.py : add licence and version to gguf writer (#6504)
·
Apr 05, 2024
b2613
87e21bba
·
bench : make n_batch and n_ubatch configurable in Batched bench (#6500)
·
Apr 05, 2024
b2612
1b496a74
·
[SYCL] Fixed minor bug when enabling FP16 for non intel targets (#6464)
·
Apr 05, 2024
b2608
7dda1b72
·
ci: exempt master branch workflows from getting cancelled (#6486)
·
Apr 04, 2024
b2589
1ff4d9f3
·
Add OpenChat, Alpaca, Vicuna chat templates (#6397)
·
Apr 03, 2024
b2586
52604860
·
[SYCL] Disable iqx on windows as WA (#6435)
·
Apr 03, 2024
b2581
37e7854c
·
ci: bench: fix Resource not accessible by integration on PR event (#6393)
·
Mar 30, 2024
b2579
f7fc5f6c
·
split: allow --split-max-size option (#6343)
·
Mar 29, 2024
b2578
ba0c7c70
·
Vulkan k-quant mmq and ggml-backend offload functionality (#6155)
·
Mar 29, 2024
Prev
1
…
11
12
13
14
15
16
17
18
19
…
99
Next