nwpie/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2026-02-05 13:53:23 +02:00
Code Issues Packages Projects Releases Wiki Activity
7,948 Commits 540 Branches 5,431 Tags

Default Branch

master

b828e18c75 · docker : fix vulkan build (#19352) · Updated 2026-02-05 12:10:39 +02:00
 ZIP  TAR.GZ

Branches

gg/fix-sve

a8b0089a5b · ggml : remove SVE paths · Updated 2025-09-28 20:26:03 +03:00
1330
1
 ZIP  TAR.GZ
gg/fa-no-kq-pad-save

837b1b4563 · ggml : remove KQ mask padding · Updated 2025-09-28 18:10:17 +03:00
1333
6
 ZIP  TAR.GZ
llama-pull

17ca6ed540 · Implement llama-pull tool · Updated 2025-09-20 19:25:21 +03:00
1421
1
 ZIP  TAR.GZ
xsn/qwen3next_experiment

e83ef74733 · one less magic number · Updated 2025-09-20 08:58:36 +03:00
1440
6
 ZIP  TAR.GZ
gg/metal-fuse-add-rms

652d303b32 · metal : fuse add + rms · Updated 2025-09-18 16:29:25 +03:00
1438
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 11:31:59 +03:00
1443
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 15:46:57 +03:00
1479
2
 ZIP  TAR.GZ
gg/metal-async

3f62ee8bee · metal : back to a single queue per device · Updated 2025-09-09 17:06:46 +03:00
1521
9
 ZIP  TAR.GZ
gg/metal-async-save-global-queue

3f62ee8bee · metal : back to a single queue per device · Updated 2025-09-09 17:06:46 +03:00
1521
9
 ZIP  TAR.GZ
rewrite-llama-run-to-be-llama-server-based

7b717fb4b2 · Rewrite llama-run to use llama-server · Updated 2025-09-05 19:22:36 +03:00
1558
1
 ZIP  TAR.GZ
gg/metal-f16

9f2636b7dc · wip · Updated 2025-09-01 11:17:56 +03:00
1607
1
 ZIP  TAR.GZ
gg/encode-pad-equal

4317d5abf5 · wip · Updated 2025-08-28 13:55:21 +03:00
1641
1
 ZIP  TAR.GZ
compilade/fix-ssm-scan-groups

dc2187d48d · ggml : fix SSM_SCAN for n_groups > 1 · Updated 2025-08-28 00:37:04 +03:00
1646
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 16:57:15 +03:00
1691
1
 ZIP  TAR.GZ
compilade/fix-qp-iq1-problems

fb573f4440 · ggml-quants : avoid division by zero in make_q3_quants · Updated 2025-08-18 01:26:02 +03:00
1761
2
 ZIP  TAR.GZ
gg/graph-prec

220860aa0c · graph : use F32 accumulators for gpt-oss · Updated 2025-08-14 16:08:31 +03:00
1788
1
 ZIP  TAR.GZ
compilade/imatrix-mxfp4

d9b625edb6 · ggml-quants : handle imatrix for MXFP4 · Updated 2025-08-12 05:12:10 +03:00
1814
1
 ZIP  TAR.GZ
compilade/gguf-py-mxfp4

2763dc8b53 · ggml-quants : handle zero amax for MXFP4 · Updated 2025-08-06 23:26:25 +03:00
1852
2
 ZIP  TAR.GZ
compilade/imatrix-neutral-prior
Some checks failed
Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Has been cancelled
Python check requirements.txt / check-requirements (push) Has been cancelled
Python Type-Check / pyright type-check (push) Has been cancelled

ea5e55d03e · Merge branch 'master' into compilade/imatrix-neutral-prior · Updated 2025-08-05 20:34:40 +03:00
1854
4
 ZIP  TAR.GZ
0cc4m/vulkan-op-opt-step-sgd
Some checks failed
Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Has been cancelled
Python check requirements.txt / check-requirements (push) Has been cancelled
Python Type-Check / pyright type-check (push) Has been cancelled
Update Operations Documentation / update-ops-docs (push) Has been cancelled

2ec70c964b · tests: Fix OPT_STEP_SGD test-backend-ops · Updated 2025-08-05 07:57:14 +03:00
1860
4
 ZIP  TAR.GZ