llama.cpp

server : add more information about error (#10455)

#1261:Commit 9fd8c2687f pushed by root

master

2024-11-27 02:09:49 +00:00

0s

[SYCL] Fix building Win package for oneAPI 2025.0 update (#10483)

#1247:Commit 5a8987793f pushed by root

master

2024-11-25 20:29:54 +00:00

0s

flake.lock: Update (#10470)

#1234:Commit cce5a90075 pushed by root

master

2024-11-25 12:19:54 +00:00

0s

ggml : do not use ARM features not included in the build (#10457)

#1212:Commit 55ed008b2d pushed by root

master

2024-11-24 19:59:53 +00:00

0s

ci: Update oneAPI runtime dll packaging (#10428)

#1200:Commit 6dfcfef078 pushed by root

master

2024-11-23 14:09:49 +00:00

0s

cuda : optimize argmax (#10441)

#1193:Commit a5e47592b6 pushed by root

master

2024-11-22 10:50:04 +00:00

0s

llama : handle KV shift for recurrent models (#10402)

#1187:Commit 1bb30bf28c pushed by root

master

2024-11-21 18:29:52 +00:00

0s

cmake: add link dependencies to cmake find pkg (#10433)

#1179:Commit f95caa7954 pushed by root

master

2024-11-21 10:19:53 +00:00

0s

vulkan: copy iq4_nl LUT into shared memory (#10409)

#1173:Commit 8fd4b7fa29 pushed by root

master

2024-11-20 17:59:53 +00:00

0s

Fix missing file renames in Makefile due to changes in commit ae8de6d50a (#10413)

#1164:Commit 3952a221af pushed by root

master

2024-11-20 09:49:52 +00:00

0s

Add required ggml-base and backend libs to cmake pkg (#10407)

#1153:Commit 2a11b6b094 pushed by root

master

2024-11-20 01:39:53 +00:00

0s

llama : add OLMo November 2024 support (#10394)

#1144:Commit a88ad007de pushed by root

master

2024-11-19 17:29:53 +00:00

0s

sycl: Revert MUL_MAT_OP support changes (#10385)

#1140:Commit 557924f222 pushed by root

master

2024-11-19 09:19:54 +00:00

0s

Skip searching root path for cross-compile builds (#10383)

#1133:Commit 531cb1c233 pushed by root

master

2024-11-19 01:09:53 +00:00

0s

docker: use GGML_NATIVE=OFF (#10368)

#1126:Commit 75207b3a88 pushed by root

master

2024-11-18 16:59:53 +00:00

0s

CUDA: remove DMMV, consolidate F16 mult mat vec (#10318)

#1113:Commit c3ea58aca4 pushed by root

master

2024-11-18 00:39:53 +00:00

0s

docs : vulkan build instructions to use git bash mingw64 (#10303)

#1104:Commit 0fff7fd798 pushed by root

master

2024-11-17 08:19:53 +00:00

0s

server: (web UI) Add samplers sequence customization (#10255)

#1098:Commit bcdb7a2386 pushed by root

master

2024-11-17 00:09:52 +00:00

0s

vulkan: Optimize some mat-vec mul quant shaders (#10296)

#1090:Commit 772703c8ff pushed by root

master

2024-11-16 15:59:54 +00:00

0s

Make updates to fix issues with clang-cl builds while using AVX512 flags (#10314)

#1079:Commit 74d73dc85c pushed by root

master

2024-11-16 07:49:54 +00:00

0s

cmake : fix ppc64 check (whisper/0)

#1076:Commit 09ecbcb596 pushed by root

master

2024-11-15 23:39:53 +00:00

0s

cann: dockerfile and doc adjustment (#10302)

#1070:Commit 231f9360d9 pushed by root

master

2024-11-15 15:29:53 +00:00

0s

ggml : build backends as libraries (#10256)

#1064:Commit ae8de6d50a pushed by root

master

2024-11-15 07:19:54 +00:00

0s

CUDA: no -sm row for very small matrices (#10185)

#1059:Commit 4a8ccb37ad pushed by root

master

2024-11-14 23:09:54 +00:00

0s

vulkan: Optimize binary ops (#10270)

#1050:Commit af148c9386 pushed by root

master

2024-11-14 14:59:52 +00:00

0s

vulkan: Use macros to make the mat mul pipeline creation more concise (#10259)

#1043:Commit 66798e42fb pushed by root

master

2024-11-14 06:49:54 +00:00

0s

docs : update bindings list (#10261)

#1035:Commit 1ee9eea094 pushed by root

master

2024-11-13 22:39:52 +00:00

0s

vulkan: Throttle the number of shader compiles during the build step. (#10222)

#1018:Commit 54ef9cfc72 pushed by root

master

2024-11-13 02:09:49 +00:00

0s

metal : more precise Q*K in FA vec kernel (#10247)

#1013:Commit b0cefea58a pushed by root

master

2024-11-11 21:39:52 +00:00

0s

vulkan: Fix newly added tests for permuted mul_mat and 1D im2col (#10226)

#1001:Commit 160687b3ed pushed by root

master

2024-11-11 13:30:35 +00:00

0s