upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-01 02:17:42 -05:00
Code Issues Packages Projects Releases Wiki Activity
11,323 Commits 825 Branches 7,693 Tags

Default Branch

master

f11d642a27 · HIP: avoid treating CDNA as dgx spark for gqa_ratio 20 in fattn_mma dqk 576 (#29572) · Updated 2026-10-01 00:51:38 -05:00
 ZIP  TAR.GZ

Branches

gg/metal-refactor-mv-2

70b063a550 · metal : reduce register pressure · Updated 2025-03-26 14:24:28 -05:00    upstream-archive

6373
8
 ZIP  TAR.GZ
gg/mamba-fix-squeeze

20b256e0fd · convert : match ssm_conv tensors by type · Updated 2025-03-25 13:29:22 -05:00    upstream-archive

6366
2
 ZIP  TAR.GZ
gg/repack-fix-mul-mat-id

e94c2bd360 · ggml : improve repack templates · Updated 2025-03-25 02:42:31 -05:00    upstream-archive

6378
2
 ZIP  TAR.GZ
sycl/disable_reorder_opt

b8b7885484 · SYCL: disable Q4_0 reorder optimization · Updated 2025-03-24 23:44:11 -05:00    upstream-archive

6371
1
 ZIP  TAR.GZ
compilade/optimal-rounding

a5b1943912 · ggml-quants : fix some edge cases in make_qkxh_nl_quants · Updated 2025-03-23 16:59:37 -05:00    upstream-archive

6382
13
 ZIP  TAR.GZ
compilade/superbpe

35c2f8b9ff · llama-vocab : add SuperBPE pre-tokenizer · Updated 2025-03-23 15:19:11 -05:00    upstream-archive

6379
1
 ZIP  TAR.GZ
xsn/private_batch_api_pooling_none

b8b173274d · server : remove old commented code [no ci] · Updated 2025-03-20 11:20:54 -05:00    upstream-archive

6409
45
 ZIP  TAR.GZ
xsn/private_batch_api

7a3c178d78 · speculative : adapt to new llama API · Updated 2025-03-18 15:05:44 -05:00    upstream-archive

6409
36
 ZIP  TAR.GZ
gg/context-fix-enc-attn-type

29acf2cf05 · context : move the change to llama_context::encode() · Updated 2025-03-18 04:55:19 -05:00    upstream-archive

6413
2
 ZIP  TAR.GZ
jg/cuda-fa-np-runtime

f6711cef44 · CUDA: determine FA parallel blocks at runtime · Updated 2025-03-16 08:36:57 -05:00    upstream-archive

6481
1
 ZIP  TAR.GZ
gg/hparams-swa-rope

c4aca65582 · hparams : add SWA rope parameters · Updated 2025-03-13 12:26:09 -05:00    upstream-archive

6440
1
 ZIP  TAR.GZ
gg/swa-fix-kv-shift

21fe0ce4eb · hparams : add comment [no ci] · Updated 2025-03-13 10:56:38 -05:00    upstream-archive

6441
2
 ZIP  TAR.GZ
gg/infill-better-stop

ed58975f51 · server : improve infill stop criteria · Updated 2025-03-12 08:28:48 -05:00    upstream-archive

6452
1
 ZIP  TAR.GZ
0cc4m/vulkan-print-coopmat-shapes

87dae2fd15 · Vulkan: Print coopmat shapes, then exit · Updated 2025-03-09 05:53:55 -05:00    upstream-archive

6466
1
 ZIP  TAR.GZ
0cc4m/vulkan-device-architecture

25840747e6 · Vulkan: Add device architecture enum and logic to recognize AMD generations · Updated 2025-03-08 02:04:45 -06:00    upstream-archive

6646
2
 ZIP  TAR.GZ
gg/server-infill-end-on-nl

c75753a01b · server : infill gen ends on new line · Updated 2025-03-07 09:19:55 -06:00    upstream-archive

6469
1
 ZIP  TAR.GZ
gg/ci-fix-save-load

aefa65e442 · ci : fix save-load test invokations · Updated 2025-03-07 04:17:33 -06:00    upstream-archive

6474
1
 ZIP  TAR.GZ
gg/clang-tidy-disable-bugprone

aae2903e0b · clang-tidy : disable bugprone-branch-clone · Updated 2025-03-07 03:36:55 -06:00    upstream-archive

6475
1
 ZIP  TAR.GZ
gg/llama-kv-cache

624f7bd03b · graph : add comments · Updated 2025-02-28 13:13:08 -06:00    upstream-archive

6539
95
 ZIP  TAR.GZ
gg/speculative-update

0f2bf55502 · speculative : do not discard the last drafted token · Updated 2025-02-19 01:21:39 -06:00    upstream-archive

6582
2
 ZIP  TAR.GZ