upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-02 02:47:26 -05:00
Code Issues Packages Projects Releases Wiki Activity
11,350 Commits 830 Branches 7,717 Tags

Default Branch

master

254b177307 · ci : fix missing zdnn backend check (#29837) · Updated 2026-10-02 02:10:45 -05:00
 ZIP  TAR.GZ

Branches

xsn/dsv4_vision_prob_bias

316ed8aade · nits · Updated 2026-09-02 09:46:27 -05:00
583
2
 ZIP  TAR.GZ
xsn/dsv4_vision

3a798bf2f3 · correct token count · Updated 2026-09-01 05:37:26 -05:00
621
7
 ZIP  TAR.GZ
nikwen/autorelease-pools

8330dcc41e · metal : fix another missing pool warning · Updated 2026-09-01 04:29:01 -05:00
676
3
 ZIP  TAR.GZ
gg/ci-disable-native

f32615d176 · ci : disable native builds for some jobs · Updated 2026-09-01 01:56:36 -05:00
619
1
 ZIP  TAR.GZ
gg/metal-fa-sparse-rpc

d2f41b65d5 · rpc: allow -sm tensor · Updated 2026-08-31 14:26:26 -05:00
625
10
 ZIP  TAR.GZ
gg/metal-fa-sparse-save-2

cd3a488320 · cont : adjust nsg · Updated 2026-08-31 13:26:45 -05:00
626
10
 ZIP  TAR.GZ
gg/test-vulkan-fail

9723942adc · hexagon: fix CPY fence bug (#28033) · Updated 2026-08-30 13:18:24 -05:00
639
0
 Included
 ZIP  TAR.GZ
xsn/tensor_read_lazy_improve

cda6f9e3a0 · Merge remote-tracking branch 'origin/master' into xsn/tensor_read_lazy_improve · Updated 2026-08-28 15:59:01 -05:00
671
3
 ZIP  TAR.GZ
tmp-q4

f91123d2d0 · qwen4exp: fix sparse-attention block selection · Updated 2026-08-28 13:38:14 -05:00
677
1
 ZIP  TAR.GZ
xsn/fix_lazy_tensor

6bfbc89820 · convert: prevent ndarray conversion in LazyChunkedTensor · Updated 2026-08-28 04:25:42 -05:00
680
1
 ZIP  TAR.GZ
allozaur/feat/models-discover-and-download

a22c1d344e · ui : apply ESLint formatting to models discover components · Updated 2026-08-28 02:42:04 -05:00
684
17
 ZIP  TAR.GZ
xsn/quant_stream

f47ff9b250 · quantize: row-slab stream to avoid thread starvation · Updated 2026-08-27 15:42:22 -05:00
688
1
 ZIP  TAR.GZ
xsn/dflash2

4e2f54f8f3 · revert top-k.cu changes · Updated 2026-08-27 12:08:52 -05:00
693
2
 ZIP  TAR.GZ
pr-27742-tmp

3d7baaebb4 · Merge remote-tracking branch 'origin/master' into qwen4exp/qwen3.8-flash-next · Updated 2026-08-27 11:32:21 -05:00
694
57
 ZIP  TAR.GZ
xsn/tensor_rows_lazy

937fe54d11 · address comments · Updated 2026-08-27 06:55:55 -05:00
703
5
 ZIP  TAR.GZ
xsn/quant_cap

c0c7fa930d · quantize: cap working memory size to avoid loading big tensors onto RAM · Updated 2026-08-27 06:48:24 -05:00
703
1
 ZIP  TAR.GZ
allozaur/feat/chat-form-actions/model-selector-ux

db97713d10 · ui: split model option icons into capabilities and modalities · Updated 2026-08-27 06:08:04 -05:00
700
15
 ZIP  TAR.GZ
xsn/video_args

4e69771682 · add mtmd_helper_init_opt · Updated 2026-08-27 04:27:48 -05:00
708
5
 ZIP  TAR.GZ
allozaur/feat/chat-form-actions/tool-policy

0cfa2beec7 · ui: remove dead MCP resources menu trigger chain · Updated 2026-08-27 04:20:55 -05:00
706
34
 ZIP  TAR.GZ
xsn/kv_track_token_id

2bd7078179 · add get_prev_tokens · Updated 2026-08-26 14:39:07 -05:00
711
4
 ZIP  TAR.GZ