tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 19:55:04 +00:00
Code Issues Packages Projects Releases Wiki Activity
5,763 Commits 442 Branches 3,853 Tags

Default Branch

master

8846aace49 · model : gemma3n text-only (#14400) · Updated 2025-06-26 17:34:02 +00:00
 ZIP  TAR.GZ

Branches

sycl/fix_exp

8b5ea7ad67 · SYCL: Take improvements from GLU branch and disable faulty fp16 exp after update · Updated 2025-06-26 14:18:58 +00:00
2
1
 ZIP  TAR.GZ
gg/llama-high-throughput

6179578988 · batch : require non-coupled batch with sequential split_equal · Updated 2025-06-25 14:20:46 +00:00
11
25
 ZIP  TAR.GZ
cisc/assistant-prefilling-content-array

2aac8e81b0 · add tests · Updated 2025-06-24 12:02:34 +00:00
3
3
 ZIP  TAR.GZ
compilade/imatrix-batched-chunks

e33de128c7 · common : move string_remove_suffix from quantize and imatrix · Updated 2025-06-23 20:24:06 +00:00
8
27
 ZIP  TAR.GZ
compilade/mamba2

afdb669206 · Merge branch 'master' into compilade/mamba2 · Updated 2025-06-23 14:40:16 +00:00
8
41
 ZIP  TAR.GZ
gg/kv-cache-use-set-rows

36f8e20d08 · kv-cache : utilize ggml_set_rows broadcast · Updated 2025-06-23 10:22:51 +00:00
11
18
 ZIP  TAR.GZ
cisc/unary-reglu-geglu-swiglu

ab46d11de5 · Refactor: Optimize SYCL element-wise operations with unary function inlining · Updated 2025-06-22 13:51:19 +00:00
20
19
 ZIP  TAR.GZ
gg/metal-fix-thread-safety

ae96333923 · metal : fix thread-safety · Updated 2025-06-20 13:42:54 +00:00
37
1
 ZIP  TAR.GZ
gg/repack-fix-wsize

6fb2f2e8a9 · ggml : fix repack work size for mul_mat_id · Updated 2025-06-20 07:34:16 +00:00
40
1
 ZIP  TAR.GZ
vb/add-smollm3

6201b43814 · Update the graph. · Updated 2025-06-19 15:13:28 +00:00
67
4
 ZIP  TAR.GZ
compilade/test-model-random

ccb2bb9988 · test-model-random : show max error · Updated 2025-06-18 19:11:23 +00:00
67
9
 ZIP  TAR.GZ
gabe-l-hart/HybridRecurrentCache

59fee24c72 · recurrent : rework graph inputs + add TODOs · Updated 2025-06-18 06:29:51 +00:00
64
31
 ZIP  TAR.GZ
add-pidfile

d3d06debe3 · server : add pidfile option · Updated 2025-06-17 20:47:53 +00:00
65
1
 ZIP  TAR.GZ
0cc4m/vulkan-fix-host-memory-max-size

4b2233befb · Vulkan: Set device max size for host memory to avoid OOM warning and fallback to CPU buffer · Updated 2025-06-17 20:25:42 +00:00
67
1
 ZIP  TAR.GZ
gg/server-reenable-swa-spec

36fce98281 · server : re-enable swa speculative decoding · Updated 2025-06-12 08:51:15 +00:00
108
1
 ZIP  TAR.GZ
gg/batch-simplify-output

ed99a8ea04 · cont : fix comments · Updated 2025-06-12 07:43:55 +00:00
111
3
 ZIP  TAR.GZ
compilade/fix-batch-reserve-rwkv

4b6fb6524b · context : round n_tokens to next multiple of n_seqs when reserving · Updated 2025-06-11 20:19:17 +00:00
114
1
 ZIP  TAR.GZ
compilade/readonly-recurrent-inputs

62a9f34bae · llama-graph : fix recurrent state copy · Updated 2025-06-10 04:26:30 +00:00
138
3
 ZIP  TAR.GZ
gg/kv-fix-shift

c257a8871c · cont : fix defrag erasing cells that didn't move · Updated 2025-06-09 17:45:56 +00:00
145
3
 ZIP  TAR.GZ
graph-profiler

ca407742c5 · profiler: initial support for profiling graph ops · Updated 2025-06-05 21:38:13 +00:00
181
1
 ZIP  TAR.GZ