upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-02 08:00:48 -05:00
Code Issues Packages Projects Releases Wiki Activity
10,228 Commits 643 Branches 6,966 Tags

Default Branch

master

596a5795bd · DeepseekV4 MTP + DSpark (#25784) · Updated 2026-08-02 07:55:34 -05:00
 ZIP  TAR.GZ

Branches

gg/llama-high-throughput-save2

6179578988 · batch : require non-coupled batch with sequential split_equal · Updated 2025-06-25 09:20:46 -05:00    upstream-archive

4486
29
 ZIP  TAR.GZ
gg/llama-high-throughput-save

37bdfbef8c · wip 3 · Updated 2025-06-24 03:04:18 -05:00    upstream-archive

4486
21
 ZIP  TAR.GZ
gg/metal-fix-thread-safety

ae96333923 · metal : fix thread-safety · Updated 2025-06-20 08:42:54 -05:00    upstream-archive

4512
1
 ZIP  TAR.GZ
gg/repack-fix-wsize

6fb2f2e8a9 · ggml : fix repack work size for mul_mat_id · Updated 2025-06-20 02:34:16 -05:00    upstream-archive

4515
1
 ZIP  TAR.GZ
gabe-l-hart/HybridRecurrentCache

59fee24c72 · recurrent : rework graph inputs + add TODOs · Updated 2025-06-18 01:29:51 -05:00    upstream-archive

4539
31
 ZIP  TAR.GZ
add-pidfile

d3d06debe3 · server : add pidfile option · Updated 2025-06-17 15:47:53 -05:00    upstream-archive

4540
1
 ZIP  TAR.GZ
gg/server-reenable-swa-spec

36fce98281 · server : re-enable swa speculative decoding · Updated 2025-06-12 03:51:15 -05:00    upstream-archive

4583
1
 ZIP  TAR.GZ
gg/batch-simplify-output

ed99a8ea04 · cont : fix comments · Updated 2025-06-12 02:43:55 -05:00    upstream-archive

4586
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 15:19:17 -05:00    upstream-archive

4589
1
 ZIP  TAR.GZ
compilade/readonly-recurrent-inputs

62a9f34bae · llama-graph : fix recurrent state copy · Updated 2025-06-09 23:26:30 -05:00    upstream-archive

4613
3
 ZIP  TAR.GZ
gg/kv-fix-shift

c257a8871c · cont : fix defrag erasing cells that didn't move · Updated 2025-06-09 12:45:56 -05:00    upstream-archive

4620
3
 ZIP  TAR.GZ
maxk/sched-prio-updates

ac35e50c16 · Update tools/llama-bench/llama-bench.cpp · Updated 2025-05-31 17:38:37 -05:00    upstream-archive

4680
3
 ZIP  TAR.GZ
cisc/test-tokenizers-remote

d3a2eb592d · disable on windows · Updated 2025-05-31 16:17:18 -05:00    upstream-archive

4671
12
 ZIP  TAR.GZ
gg/min-p-fix

9065ca71a2 · tests : sampling tests use min_keep == 0 · Updated 2025-05-27 03:30:41 -05:00    upstream-archive

4726
3
 ZIP  TAR.GZ
gg/tts-fix-ubatch

108d484ab2 · tts : fix n_ubatch + make WavTokenizer cache-less · Updated 2025-05-22 13:58:10 -05:00    upstream-archive

4770
1
 ZIP  TAR.GZ
jared/permit-causal-encode

b06a954bbc · llama_encode : only force non-causal attention for enc-dec models · Updated 2025-05-19 12:43:59 -05:00    upstream-archive

4803
1
 ZIP  TAR.GZ
gg/bench-handle-decode-errors

8282d74692 · bench : handle decode errors · Updated 2025-05-14 14:36:29 -05:00    upstream-archive

4841
1
 ZIP  TAR.GZ
gg/server-models-loading

237acc7cd5 · server : update readme + return json for "meta" field · Updated 2025-05-14 07:30:12 -05:00    upstream-archive

4850
2
 ZIP  TAR.GZ
gg/metal-fa-vec-bs20

78d70223c3 · metal : use FA-vec kernel up to batch size 20 · Updated 2025-05-13 02:38:06 -05:00    upstream-archive

4867
3
 ZIP  TAR.GZ
gg/context-remove-logits-all

6107303ab0 · llama : remove logits_all flag + reorder llama_context_params · Updated 2025-05-08 05:01:41 -05:00    upstream-archive

4920
2
 ZIP  TAR.GZ