Superminaren/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-07 20:47:30 +02:00
Code Issues Packages Projects Releases Wiki Activity
10,850 Commits 780 Branches 7,352 Tags

Default Branch

master

f114f91f9e · tests : initialize the L2_NORM batch array (#28553) · Updated 2026-09-07 19:54:13 +02:00
 ZIP  TAR.GZ

Branches

gg/server-chunked-prefill

a6648b9df7 · server : chunked prefill support · Updated 2024-12-08 08:48:18 +01:00    Superminaren

6564
1
 ZIP  TAR.GZ
jg/gguf-refactor

a8046c888a · use calloc instead of malloc · Updated 2024-12-04 17:24:35 +01:00    Superminaren

6595
3
 ZIP  TAR.GZ
gg/server-fix-spec-ctx-shift

81611bef72 · server : add tests · Updated 2024-12-04 12:11:26 +01:00    Superminaren

6595
3
 ZIP  TAR.GZ
gg/server-fix-spec

33d7b70c88 · server : do not speculate during prompt processing · Updated 2024-12-03 09:58:43 +01:00    Superminaren

6608
1
 ZIP  TAR.GZ
gg/metal-mul-mv-new-save3

3c8a2a83fe · shmem experiments · Updated 2024-11-26 14:17:38 +01:00    Superminaren

6671
3
 ZIP  TAR.GZ
gg/metal-mul-mv-new-save2

dafedd33d2 · 4x4 -> 4x · Updated 2024-11-26 13:54:02 +01:00    Superminaren

6671
2
 ZIP  TAR.GZ
gg/metal-mul-mv-new

bf3494345e · metal : some mul_mv experiments · Updated 2024-11-26 13:48:50 +01:00    Superminaren

6671
1
 ZIP  TAR.GZ
gg/speculative-infill

b83cae088c · speculative : add infill mode · Updated 2024-11-26 10:14:17 +01:00    Superminaren

6676
1
 ZIP  TAR.GZ
gg/metal-mul-mat-f16

4ff0831ce6 · metal : use F16 math in mul_mat kernels · Updated 2024-11-25 14:15:26 +01:00    Superminaren

6689
1
 ZIP  TAR.GZ
gg/logits-slowdown

f7b0233eca · wip · Updated 2024-11-16 09:33:55 +01:00    Superminaren

6751
1
 ZIP  TAR.GZ
gg/speculative-experiments

5e6dad9322 · speculative : experimenting with Qwen2.5 · Updated 2024-11-14 10:31:31 +01:00    Superminaren

6773
2
 ZIP  TAR.GZ
gg/speculative-fix-oob

33bdee667e · speculative : fix out-of-bounds access · Updated 2024-11-14 10:23:45 +01:00    Superminaren

6773
1
 ZIP  TAR.GZ
gg/metal-q4_0-opt

8c1b186cb5 · metal : minor Q4_0 optimization · Updated 2024-11-12 14:30:51 +01:00    Superminaren

6783
21
 ZIP  TAR.GZ
gg/metal-mul-mat-write-opt

3d1fe1bb4d · metal : int -> short, style · Updated 2024-11-09 09:32:16 +01:00    Superminaren

6794
2
 ZIP  TAR.GZ
gg/metal-fix-build

bd1198a67a · metal : fix build and some more comments · Updated 2024-11-09 09:09:50 +01:00    Superminaren

6794
1
 ZIP  TAR.GZ
gg/metal-fa-f16

a2385da59c · make : clean-up [no ci] · Updated 2024-11-08 12:46:20 +01:00    Superminaren

6801
9
 ZIP  TAR.GZ
gg/metal-fa-f16-save

94accca4c2 · vec move mask to shmem · Updated 2024-11-07 19:58:10 +01:00    Superminaren

6811
19
 ZIP  TAR.GZ
fix_sycl_ci

c5d8bb5a81 · leave only basic functions for SYCL CI · Updated 2024-11-06 08:47:50 +01:00    Superminaren

6876
2
 ZIP  TAR.GZ
sl/llama-bench-headers

4fc8673d09 · llama-bench : skip repeated values in consecutive lines · Updated 2024-11-02 15:37:33 +01:00    Superminaren

6836
1
 ZIP  TAR.GZ
sl/aligned-alloc-no-abort

20e12112fd · llama : suggest reduce ctx size when kv init fails · Updated 2024-11-02 00:55:19 +01:00    Superminaren

6839
2
 ZIP  TAR.GZ