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

allozaur/feat/external-llama-server-backends

ccc4ae694d · ui : give models one mark · Updated 2026-09-28 05:10:14 -05:00
93
95
 ZIP  TAR.GZ
allozaur/ui/discover-dialog

5f2d7ed21c · ui : models discover dialog · Updated 2026-09-28 04:40:29 -05:00
93
13
 ZIP  TAR.GZ
maxk/hexagon-alloc-buffer-n

0c434695e0 · hex-bufs: add support for splitting large tensors into separate buffers · Updated 2026-09-27 18:06:20 -05:00
189
10
 ZIP  TAR.GZ
gg/rpc-add-logs

1777b02be1 · rpc : turn GGML_RPC_DEBUG into a verbosity level and add logs · Updated 2026-09-27 15:00:44 -05:00
129
1
 ZIP  TAR.GZ
aman/sparse-unified

7908e9e8ce · llama + CUDA: flash_attn_ext_rows (fix unified kv for multi-seq) · Updated 2026-09-27 02:32:38 -05:00
142
1
 ZIP  TAR.GZ
aman/rpc_rdma_idle

f8bc970dfe · add TODO for apple RDMA · Updated 2026-09-26 05:53:11 -05:00
160
2
 ZIP  TAR.GZ
0cc4m/vulkan-fix-argsort-kernel-selection

069c82c36c · vulkan: fix argsort kernel selection for Adreno · Updated 2026-09-26 02:24:38 -05:00
154
1
 ZIP  TAR.GZ
revert-28849-modify_max_ctx

9461c7e4df · Revert "Change max context length for auto-fitting with unified KV (#28849)" · Updated 2026-09-25 12:14:56 -05:00
160
1
 ZIP  TAR.GZ
rpc_tensor_loading

7d8a964eb7 · RPC: improve loading · Updated 2026-09-25 00:16:34 -05:00
174
5
 ZIP  TAR.GZ
gg/metal-mm-int8

1e543758b9 · metal : add int8 mul_mat PoC using the tensor API · Updated 2026-09-24 15:53:42 -05:00
183
1
 ZIP  TAR.GZ
gg/mimo-tmp-5

a0484817c7 · convert: add support for mtp flags · Updated 2026-09-24 02:28:59 -05:00
193
4
 ZIP  TAR.GZ
aman/fix-mimo-sm-tensor

24a846524b · convert: add support for mtp flags · Updated 2026-09-24 01:44:22 -05:00
288
4
 ZIP  TAR.GZ
gg/mimo-tmp-4

24a846524b · convert: add support for mtp flags · Updated 2026-09-24 01:44:22 -05:00
288
4
 ZIP  TAR.GZ
gg/mimi-tmp-3

294fc70ca0 · tmp · Updated 2026-09-24 00:29:07 -05:00
197
1
 ZIP  TAR.GZ
gg/make-release-desc-link-prev-release

c995cb4b9e · scripts : make-release-desc - link previous release in changelog title · Updated 2026-09-23 12:56:28 -05:00
203
1
 ZIP  TAR.GZ
cisc/ci-amd-gfx1201-jobs

1c911f1ef9 · fix name · Updated 2026-09-23 07:06:16 -05:00
212
2
 ZIP  TAR.GZ
cisc/cuda-fuse-grouped-experts

4ffcbaf2ae · add to graph_optimize · Updated 2026-09-23 03:01:35 -05:00
30
3
 ZIP  TAR.GZ
xsn/n_embd_inp_enc

13baab725f · llama: sanity check for dflash n_embd_inp_enc and qwen4 ple_n_heads · Updated 2026-09-22 14:43:20 -05:00
239
1
 ZIP  TAR.GZ
maxk/smaller-sampler-probe

11bb9e571d · sampler: reduce the size of the probe · Updated 2026-09-22 14:08:58 -05:00
239
1
 ZIP  TAR.GZ
gg/jinja-fix-dangling-reference

f0fffd6c37 · jinja : fix dangling reference warning in for_statement · Updated 2026-09-22 12:40:09 -05:00
239
1
 ZIP  TAR.GZ