kanshan/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-05 18:50:21 +00:00
Code Issues Packages Projects Releases Wiki Activity
9,878 Commits 613 Branches 6,723 Tags

Default Branch

master

2da6686176 · Fix stale tensor-split params for draft models (#24814) · Updated 2026-07-05 18:39:36 +00:00
 ZIP  TAR.GZ

Branches

gg/kv-fix-shift

c257a8871c · cont : fix defrag erasing cells that didn't move · Updated 2025-06-09 17:45:56 +00:00    kanshan

4251
3
 ZIP  TAR.GZ
maxk/sched-prio-updates

ac35e50c16 · Update tools/llama-bench/llama-bench.cpp · Updated 2025-05-31 22:38:37 +00:00    kanshan

4311
3
 ZIP  TAR.GZ
cisc/test-tokenizers-remote

d3a2eb592d · disable on windows · Updated 2025-05-31 21:17:18 +00:00    kanshan

4302
12
 ZIP  TAR.GZ
gg/min-p-fix

9065ca71a2 · tests : sampling tests use min_keep == 0 · Updated 2025-05-27 08:30:41 +00:00    kanshan

4357
3
 ZIP  TAR.GZ
gg/tts-fix-ubatch

108d484ab2 · tts : fix n_ubatch + make WavTokenizer cache-less · Updated 2025-05-22 18:58:10 +00:00    kanshan

4401
1
 ZIP  TAR.GZ
jared/permit-causal-encode

b06a954bbc · llama_encode : only force non-causal attention for enc-dec models · Updated 2025-05-19 17:43:59 +00:00    kanshan

4453
1
 ZIP  TAR.GZ
gg/bench-handle-decode-errors

8282d74692 · bench : handle decode errors · Updated 2025-05-14 19:36:29 +00:00    kanshan

4491
1
 ZIP  TAR.GZ
gg/server-models-loading

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

4500
2
 ZIP  TAR.GZ
gg/metal-fa-vec-bs20

78d70223c3 · metal : use FA-vec kernel up to batch size 20 · Updated 2025-05-13 07:38:06 +00:00    kanshan

4517
3
 ZIP  TAR.GZ
gg/context-remove-logits-all

6107303ab0 · llama : remove logits_all flag + reorder llama_context_params · Updated 2025-05-08 10:01:41 +00:00    kanshan

4570
2
 ZIP  TAR.GZ
gg/metal-mm-pad

16843dba33 · metal : pad mm results · Updated 2025-05-04 06:13:52 +00:00    kanshan

4606
1
 ZIP  TAR.GZ
jg/llama-opt-3

15dea7bbdf · opt : remove print [no ci] · Updated 2025-05-02 18:25:29 +00:00    kanshan

4610
4
 ZIP  TAR.GZ
sync-ggml-25-05-01

65202d2985 · sync : ggml · Updated 2025-05-01 06:59:02 +00:00    kanshan

4641
3
 ZIP  TAR.GZ
gg/survey-nvidia

b710758323 · readme : update hot topics · Updated 2025-04-28 08:04:28 +00:00    kanshan

4675
1
 ZIP  TAR.GZ
cedo/fix-q25vl

37ae6a281a · Fixes Qwen2.5VL segfault during inference with https://github.com/ggml-org/llama.cpp/pull/12402 as has_qwen2vl_merger migration was incomplete · Updated 2025-04-27 10:36:57 +00:00    kanshan

4682
1
 ZIP  TAR.GZ
gg/model-cards

ed68474f76 · wip · Updated 2025-04-25 16:07:09 +00:00    kanshan

4705
2
 ZIP  TAR.GZ
compilade/parallel-convert

3fe362fe49 · gguf-py : use ThreadPoolExecutor when writing tensors · Updated 2025-04-12 04:00:51 +00:00    kanshan

4761
4
 ZIP  TAR.GZ
gg/test-fp16

098f0e5eea · test · Updated 2025-04-10 09:35:16 +00:00    kanshan

4781
1
 ZIP  TAR.GZ
revert-12734-fix_code_in_ggmlsycl

e9e1882d2d · rm tail space · Updated 2025-04-08 05:43:11 +00:00    kanshan

4804
4
 ZIP  TAR.GZ
compilade/lazy-tuples

da140da72a · gguf-py : fix flake8 lint · Updated 2025-04-07 23:38:35 +00:00    kanshan

4804
2
 ZIP  TAR.GZ