CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity
6,853 Commits 495 Branches 4,623 Tags

Default Branch

master

945501f5ea · llama: fix leaked buffers for mmap + split files (#16765) · Updated 2025-10-27 08:17:31 +00:00
 ZIP  TAR.GZ

Branches

feat/s390x-cpu-feats

f5e2392e05 · devops: update release workflow · Updated 2025-10-26 06:34:35 +00:00
48
13
 ZIP  TAR.GZ
0cc4m/vulkan-mmq-dp4a-k-quants

7984fc57e0 · Pack q2_k blocks into caches of 32 · Updated 2025-10-25 13:31:42 +00:00
23
2
 ZIP  TAR.GZ
compilade/fix-prequant-mxfp4-gpt-oss

d7f794eadb · convert : avoid dequantizing mxfp4 for GPT-OSS · Updated 2025-10-24 11:56:26 +00:00
22
1
 ZIP  TAR.GZ
gg/metal-mul-mm-rework

9fce24472f · metal : bf16 workaround (tmp) · Updated 2025-10-24 10:38:11 +00:00
16
4
 ZIP  TAR.GZ
sl/auto-disable-pipeline-parallelism

96cf05ccc1 · llama : disable pipeline parallelism if compute buffer allocation fails · Updated 2025-10-23 22:49:13 +00:00
23
1
 ZIP  TAR.GZ
compilade/convert-prequant

93fbd407f3 · Merge branch 'master' into compilade/convert-prequant · Updated 2025-10-23 18:23:12 +00:00
324
5
 ZIP  TAR.GZ
gg/server-unified-slots

7a25d4b599 · wip [no ci] · Updated 2025-10-23 14:54:53 +00:00
30
6
 ZIP  TAR.GZ
gg/graph-mamba-reuse

8242d79f23 · Revert "memory : move the recurrent state into the memory context" · Updated 2025-10-21 07:12:51 +00:00
0
5
 ZIP  TAR.GZ
gg/metal-alloc-size

f0076dc5a0 · metal : adjust .get_alloc_size to be alloc friendly · Updated 2025-10-19 14:20:54 +00:00
19
1
 ZIP  TAR.GZ
graph-profiler

003326359a · profiler: output all tensor names · Updated 2025-10-16 17:53:40 +00:00
770
2
 ZIP  TAR.GZ
cisc/minja-sync-81

987fb8c04c · remove spurious semicolon · Updated 2025-10-10 14:05:53 +00:00
28
2
 ZIP  TAR.GZ
gg/fix-amx

96f9f391c7 · ggml : fix unaligned access in AMX code · Updated 2025-09-29 07:37:15 +00:00    CS348Project

137
1
 ZIP  TAR.GZ
gg/fix-sve

a8b0089a5b · ggml : remove SVE paths · Updated 2025-09-28 17:26:03 +00:00    CS348Project

137
1
 ZIP  TAR.GZ
gg/fa-no-kq-pad

837b1b4563 · ggml : remove KQ mask padding · Updated 2025-09-28 15:10:17 +00:00    CS348Project

140
6
 ZIP  TAR.GZ
llama-pull

17ca6ed540 · Implement llama-pull tool · Updated 2025-09-20 16:25:21 +00:00    CS348Project

228
1
 ZIP  TAR.GZ
xsn/qwen3next_experiment

e83ef74733 · one less magic number · Updated 2025-09-20 05:58:36 +00:00    CS348Project

247
6
 ZIP  TAR.GZ
gg/metal-fuse-add-rms

652d303b32 · metal : fuse add + rms · Updated 2025-09-18 13:29:25 +00:00    CS348Project

245
1
 ZIP  TAR.GZ
gg/metal-mul-mv-opt-2

64c6dcbe6d · metal : make the NSG a function constant in mul_mv kernels · Updated 2025-09-18 08:31:59 +00:00    CS348Project

250
2
 ZIP  TAR.GZ
gg/metal-use-virtual-gpu-address

6045c5a263 · cont : put all buffers in the same virtual address space · Updated 2025-09-14 12:46:57 +00:00    CS348Project

286
2
 ZIP  TAR.GZ
compilade/convert-reflinks

833d03c25d · convert : for FP8, use scale type to decide auto type · Updated 2025-09-09 18:36:34 +00:00    CS348Project

324
21
 ZIP  TAR.GZ