git/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp synced 2026-03-04 06:09:13 +01:00
Code Issues Packages Projects Releases Wiki Activity
8,193 Commits 543 Branches 5,623 Tags 1.2 GiB

Default Branch

master

ecd99d6a9a · docs: Fix intel documentation link (#20040) · Updated 2026-03-03 14:50:00 +01:00
 ZIP  TAR.GZ

Branches

gg/metal-fix-thread-safety

ae96333923 · metal : fix thread-safety · Updated 2025-06-20 15:42:54 +02:00
2477
1
 ZIP  TAR.GZ
gg/repack-fix-wsize

6fb2f2e8a9 · ggml : fix repack work size for mul_mat_id · Updated 2025-06-20 09:34:16 +02:00
2480
1
 ZIP  TAR.GZ
gabe-l-hart/HybridRecurrentCache

59fee24c72 · recurrent : rework graph inputs + add TODOs · Updated 2025-06-18 08:29:51 +02:00
2504
31
 ZIP  TAR.GZ
add-pidfile

d3d06debe3 · server : add pidfile option · Updated 2025-06-17 22:47:53 +02:00
2505
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 22:25:42 +02:00
2507
1
 ZIP  TAR.GZ
gg/server-reenable-swa-spec

36fce98281 · server : re-enable swa speculative decoding · Updated 2025-06-12 10:51:15 +02:00
2548
1
 ZIP  TAR.GZ
gg/batch-simplify-output

ed99a8ea04 · cont : fix comments · Updated 2025-06-12 09:43:55 +02:00
2551
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 22:19:17 +02:00
2554
1
 ZIP  TAR.GZ
compilade/readonly-recurrent-inputs

62a9f34bae · llama-graph : fix recurrent state copy · Updated 2025-06-10 06:26:30 +02:00
2578
3
 ZIP  TAR.GZ
gg/kv-fix-shift

c257a8871c · cont : fix defrag erasing cells that didn't move · Updated 2025-06-09 19:45:56 +02:00
2585
3
 ZIP  TAR.GZ
maxk/sched-prio-updates

ac35e50c16 · Update tools/llama-bench/llama-bench.cpp · Updated 2025-06-01 00:38:37 +02:00
2645
3
 ZIP  TAR.GZ
cisc/test-tokenizers-remote

d3a2eb592d · disable on windows · Updated 2025-05-31 23:17:18 +02:00
2636
12
 ZIP  TAR.GZ
gg/min-p-fix

9065ca71a2 · tests : sampling tests use min_keep == 0 · Updated 2025-05-27 10:30:41 +02:00
2691
3
 ZIP  TAR.GZ
gg/tts-fix-ubatch

108d484ab2 · tts : fix n_ubatch + make WavTokenizer cache-less · Updated 2025-05-22 20:58:10 +02:00
2735
1
 ZIP  TAR.GZ
jared/permit-causal-encode

b06a954bbc · llama_encode : only force non-causal attention for enc-dec models · Updated 2025-05-19 19:43:59 +02:00
2768
1
 ZIP  TAR.GZ
gg/bench-handle-decode-errors

8282d74692 · bench : handle decode errors · Updated 2025-05-14 21:36:29 +02:00
2806
1
 ZIP  TAR.GZ
gg/server-models-loading

237acc7cd5 · server : update readme + return json for "meta" field · Updated 2025-05-14 14:30:12 +02:00
2815
2
 ZIP  TAR.GZ
gg/metal-fa-vec-bs20

78d70223c3 · metal : use FA-vec kernel up to batch size 20 · Updated 2025-05-13 09:38:06 +02:00
2832
3
 ZIP  TAR.GZ
gg/context-remove-logits-all

6107303ab0 · llama : remove logits_all flag + reorder llama_context_params · Updated 2025-05-08 12:01:41 +02:00
2885
2
 ZIP  TAR.GZ
gg/metal-mm-pad

16843dba33 · metal : pad mm results · Updated 2025-05-04 08:13:52 +02:00
2921
1
 ZIP  TAR.GZ