upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-01 15:40:46 -05:00
Code Issues Packages Projects Releases Wiki Activity
10,222 Commits 643 Branches 6,961 Tags

Default Branch

master

a7a6d0d269 · vulkan: extend topk_moe fusion to support sqrt(softplus) (#26124) · Updated 2026-08-01 14:18:07 -05:00
 ZIP  TAR.GZ

Branches

sampling-refactor

56ba00b923 · sampling : hide prev behind API and apply #3661 · Updated 2023-10-20 10:53:27 -05:00    upstream-archive

8817
6
 ZIP  TAR.GZ
speculative-tree

ad2727d091 · Merge branch 'master' into speculative-tree · Updated 2023-10-18 02:50:58 -05:00    upstream-archive

8828
18
 ZIP  TAR.GZ
llava-fix-offloading

932589c0ef · Honor -ngl option for Cuda offloading in llava · Updated 2023-10-13 19:12:10 -05:00    upstream-archive

8842
1
 ZIP  TAR.GZ
rev-sampling

5261aee8d8 · sampling : one sequence per sampling context · Updated 2023-10-12 12:36:44 -05:00    upstream-archive

8845
1
 ZIP  TAR.GZ
batched-bench

2fcdf869cd · batched-bench : add mmq CLI arg · Updated 2023-10-11 11:42:33 -05:00    upstream-archive

8857
7
 ZIP  TAR.GZ
alloc-assert-fix

ee7456926e · ggml-alloc : fix assert in debug builds · Updated 2023-10-09 07:33:12 -05:00    upstream-archive

8866
1
 ZIP  TAR.GZ
fix-kv-cache-access

ee268b5446 · llama : no longer perform uninitialized access to the KV cache · Updated 2023-10-08 03:49:38 -05:00    upstream-archive

8873
5
 ZIP  TAR.GZ
fix-refact

acead654d2 · Merge branch 'master' into fix-refact · Updated 2023-10-08 03:25:16 -05:00    upstream-archive

8873
4
 ZIP  TAR.GZ
metal-improve-batching

6b9554a740 · metal : print more GPU info + disable mul_mm for MTLGPUFamiliy < Apple7 · Updated 2023-10-08 01:55:13 -05:00    upstream-archive

8880
5
 ZIP  TAR.GZ
gguf-fix-publish

ba44776dc2 · bump version · Updated 2023-10-07 13:47:48 -05:00    upstream-archive

8879
6
 ZIP  TAR.GZ
server-parallel

5ab6c2132a · server-parallel : add "--reverse-prompt" + compiler warning fixes · Updated 2023-10-06 06:32:19 -05:00    upstream-archive

8892
4
 ZIP  TAR.GZ
fix-sessions

5418932b71 · llama : fix comments for llama_kv_cache API · Updated 2023-10-03 13:01:52 -05:00    upstream-archive

8917
5
 ZIP  TAR.GZ
custom-attention-mask

c5650ed470 · server : avoid context swaps by shifting the KV cache · Updated 2023-09-28 11:03:36 -05:00    upstream-archive

8941
57
 ZIP  TAR.GZ
cam-simple-fix

72e7ef4e53 · simple : fixes · Updated 2023-09-26 16:19:36 -05:00    upstream-archive

8967
48
 ZIP  TAR.GZ
custom-attention-mask-no-roped-cache

784d14ed31 · llama : store non-RoPEd K cache (WIP) · Updated 2023-09-17 15:43:07 -05:00    upstream-archive

8979
5
 ZIP  TAR.GZ
support-starcoder-fix

92a4f86879 · llama : make starcoder graph build more consistent with others · Updated 2023-09-15 09:57:10 -05:00    upstream-archive

8989
20
 ZIP  TAR.GZ
mul-mat-pad

e7e7b11455 · llama : remove experimental stuff · Updated 2023-09-14 14:52:01 -05:00    upstream-archive

9001
3
 ZIP  TAR.GZ
metal-fix-norm

2f689dee06 · metal : minor · Updated 2023-09-07 07:33:21 -05:00    upstream-archive

9034
5
 ZIP  TAR.GZ
build-metal-default

30ac7a4117 · gitignore : metal · Updated 2023-09-04 14:23:16 -05:00    upstream-archive

9046
12
 ZIP  TAR.GZ
metal-cont-bug

f3a84b2e0d · llama : better express the KV cache dependencies in the graph · Updated 2023-09-04 13:44:48 -05:00    upstream-archive

9046
5
 ZIP  TAR.GZ