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

gg/metal-fuse-add-rms

652d303b32 · metal : fuse add + rms · Updated 2025-09-18 06:29:25 -07:00
934
1
 ZIP  TAR.GZ
gg/metal-mul-mv-opt-2

64c6dcbe6d · metal : make the NSG a function constant in mul_mv kernels · Updated 2025-09-18 01:31:59 -07:00
939
2
 ZIP  TAR.GZ
gg/metal-use-virtual-gpu-address

6045c5a263 · cont : put all buffers in the same virtual address space · Updated 2025-09-14 05:46:57 -07:00
975
2
 ZIP  TAR.GZ
gg/metal-async

3f62ee8bee · metal : back to a single queue per device · Updated 2025-09-09 07:06:46 -07:00
1017
9
 ZIP  TAR.GZ
gg/metal-async-save-global-queue

3f62ee8bee · metal : back to a single queue per device · Updated 2025-09-09 07:06:46 -07:00
1017
9
 ZIP  TAR.GZ
rewrite-llama-run-to-be-llama-server-based

7b717fb4b2 · Rewrite llama-run to use llama-server · Updated 2025-09-05 09:22:36 -07:00
1054
1
 ZIP  TAR.GZ
gg/metal-f16

9f2636b7dc · wip · Updated 2025-09-01 01:17:56 -07:00
1103
1
 ZIP  TAR.GZ
gg/compare-mlx

d8c17629ac · examples : add compare-mlx · Updated 2025-08-31 23:10:01 -07:00
1106
1
 ZIP  TAR.GZ
gg/encode-pad-equal

4317d5abf5 · wip · Updated 2025-08-28 03:55:21 -07:00
1137
1
 ZIP  TAR.GZ
compilade/fix-ssm-scan-groups

dc2187d48d · ggml : fix SSM_SCAN for n_groups > 1 · Updated 2025-08-27 14:37:04 -07:00
1142
1
 ZIP  TAR.GZ
0cc4m/vulkan-enable-conv2d-on-apple

7a152de3bb · vulkan: enable Conv2D for Apple after MoltenVK fixed the bug · Updated 2025-08-23 06:57:15 -07:00
1187
1
 ZIP  TAR.GZ
compilade/fix-qp-iq1-problems

fb573f4440 · ggml-quants : avoid division by zero in make_q3_quants · Updated 2025-08-17 15:26:02 -07:00
1257
2
 ZIP  TAR.GZ
gg/graph-prec

220860aa0c · graph : use F32 accumulators for gpt-oss · Updated 2025-08-14 06:08:31 -07:00
1284
1
 ZIP  TAR.GZ
compilade/imatrix-mxfp4

d9b625edb6 · ggml-quants : handle imatrix for MXFP4 · Updated 2025-08-11 19:12:10 -07:00
1310
1
 ZIP  TAR.GZ
compilade/gguf-py-mxfp4

2763dc8b53 · ggml-quants : handle zero amax for MXFP4 · Updated 2025-08-06 13:26:25 -07:00
1348
2
 ZIP  TAR.GZ
compilade/imatrix-neutral-prior

ea5e55d03e · Merge branch 'master' into compilade/imatrix-neutral-prior · Updated 2025-08-05 10:34:40 -07:00
1350
4
 ZIP  TAR.GZ
0cc4m/vulkan-op-opt-step-sgd

2ec70c964b · tests: Fix OPT_STEP_SGD test-backend-ops · Updated 2025-08-04 21:57:14 -07:00
1356
4
 ZIP  TAR.GZ
compilade/fix-output-overflow

145401c9e3 · context : fix logits size overflow for huge batches · Updated 2025-08-04 19:26:46 -07:00
1355
2
 ZIP  TAR.GZ
compilade/imatrix-gguf-warning

342e7014db · imatrix : only warn about suffix when output format is unspecified · Updated 2025-08-04 12:12:27 -07:00
1360
2
 ZIP  TAR.GZ
compilade/hybrid-kv_unified

e549515cb3 · memory : handle kv_unified for hybrid models · Updated 2025-08-02 21:45:47 -07:00
1369
1
 ZIP  TAR.GZ