happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
7,444 Commits 517 Branches 5,070 Tags 998 MiB

Default Branch

master

58062860af · ggml : use WARP_SIZE/2 for argmax reduction offset (#18092) · Updated 2025-12-16 19:47:01 -08:00
 ZIP  TAR.GZ

Branches

compilade/imatrix-saner-3d

91e67b8583 · imatrix : fix 3d tensor counts · Updated 2025-07-31 08:56:38 -07:00
1397
4
 ZIP  TAR.GZ
gg/server-test-lru

b98f80a6b4 · server : test alternative LRU logic · Updated 2025-07-29 11:19:21 -07:00
1418
1
 ZIP  TAR.GZ
xd/ops-musa

0591b39e48 · ops: add MUSA · Updated 2025-07-29 02:25:32 -07:00
1424
1
 ZIP  TAR.GZ
gg/repack-opt-mm-id

381879e0ac · cont : tmp · Updated 2025-07-28 21:42:55 -07:00
1448
3
 ZIP  TAR.GZ
gg/ot-cpu-repack

fb371c18ec · bench,common : add CPU extra buffer types · Updated 2025-07-28 11:53:18 -07:00
1425
1
 ZIP  TAR.GZ
gg/ops-update-blas

e9f7e7cce2 · ops : update BLAS · Updated 2025-07-27 23:42:57 -07:00
1435
1
 ZIP  TAR.GZ
sync-ggml-25-07-25

a5801f408f · sync : ggml · Updated 2025-07-25 04:31:39 -07:00
1454
2
 ZIP  TAR.GZ
gg/server-fix-vision-tests

6f4c57236b · server : fix vision test regex · Updated 2025-07-25 01:22:36 -07:00
1476
1
 ZIP  TAR.GZ
compilade/output-reorder-lazy-sort

e65aa69402 · context : only sort outputs when needed · Updated 2025-07-24 08:06:34 -07:00
1463
1
 ZIP  TAR.GZ
sl/sched-copy-incr-fix

a124399f19 · sched : fix multiple evaluations of the same graph with pipeline parallelism · Updated 2025-07-24 07:03:14 -07:00
1463
1
 ZIP  TAR.GZ
gg/context-sync-upon-output-reorder

978c88ba0a · cont : add TODO · Updated 2025-07-24 06:31:10 -07:00
1465
2
 ZIP  TAR.GZ
compilade/imatrix-gguf-default

1ef3cc1a87 · imatrix : use GGUF regardless of the output filename · Updated 2025-07-23 20:22:41 -07:00
1470
2
 ZIP  TAR.GZ
gg/fix-fa-q-non-cont

55cf48de1e · cuda : fix multi-seq, quantized FA · Updated 2025-07-22 10:48:53 -07:00
1512
2
 ZIP  TAR.GZ
0cc4m/vulkan-fprintf-fix

0a0af0dbbd · Vulkan: Fix fprintf format-security warning · Updated 2025-07-19 02:45:31 -07:00
1506
1
 ZIP  TAR.GZ
sync-ggml-25-07-19

386892ec61 · sync : ggml · Updated 2025-07-19 01:46:12 -07:00
1507
1
 ZIP  TAR.GZ
gg/graph-reuse-reset-fix

cfe5e98423 · graph : fix graph reuse reset of params · Updated 2025-07-18 07:50:32 -07:00
1510
1
 ZIP  TAR.GZ
gg/fix-build-gf

9106d7595d · model : fix build after merge conflict · Updated 2025-07-18 01:50:59 -07:00
1513
1
 ZIP  TAR.GZ
gg/unified-fix-k-shift

05baa62a73 · kv-cache : fix k-shift for multiple streams · Updated 2025-07-17 10:18:36 -07:00
1522
1
 ZIP  TAR.GZ
gg/server-eos-pre-calc

07908a824a · server : pre-calculate EOG logit biases · Updated 2025-07-16 03:47:05 -07:00
1535
1
 ZIP  TAR.GZ
gg/server-fix-ignore-eos

9f8d285901 · server : fix handling of the ignore_eos flag · Updated 2025-07-15 21:37:18 -07:00
1540
1
 ZIP  TAR.GZ