Default Branch

596a5795bd · DeepseekV4 MTP + DSpark (#25784) · Updated 2026-08-02 07:55:34 -05:00

Branches

16843dba33 · metal : pad mm results · Updated 2025-05-04 01:13:52 -05:00    upstream-archive

4956
1

15dea7bbdf · opt : remove print [no ci] · Updated 2025-05-02 13:25:29 -05:00    upstream-archive

4960
4

65202d2985 · sync : ggml · Updated 2025-05-01 01:59:02 -05:00    upstream-archive

4991
3

b710758323 · readme : update hot topics · Updated 2025-04-28 03:04:28 -05:00    upstream-archive

5025
1

37ae6a281a · Fixes Qwen2.5VL segfault during inference with https://github.com/ggml-org/llama.cpp/pull/12402 as has_qwen2vl_merger migration was incomplete · Updated 2025-04-27 05:36:57 -05:00    upstream-archive

5032
1

ed68474f76 · wip · Updated 2025-04-25 11:07:09 -05:00    upstream-archive

5055
2

3fe362fe49 · gguf-py : use ThreadPoolExecutor when writing tensors · Updated 2025-04-11 23:00:51 -05:00    upstream-archive

5111
4

098f0e5eea · test · Updated 2025-04-10 04:35:16 -05:00    upstream-archive

5131
1

e9e1882d2d · rm tail space · Updated 2025-04-08 00:43:11 -05:00    upstream-archive

5154
4

da140da72a · gguf-py : fix flake8 lint · Updated 2025-04-07 18:38:35 -05:00    upstream-archive

5154
2

ced26486ff · cont · Updated 2025-04-07 07:24:01 -05:00    upstream-archive

5166
6

fe564b0dfb · ci : rename job MSVC -> MinGW · Updated 2025-04-04 05:51:48 -05:00    upstream-archive

5181
1

43ab09b85d · ci : testing (wip) · Updated 2025-04-04 05:43:43 -05:00    upstream-archive

5181
1

7a73e861a7 · cont · Updated 2025-04-04 04:02:20 -05:00    upstream-archive

5190
4

c875e03f96 · rpc : update README for cache usage · Updated 2025-03-28 02:41:47 -05:00    upstream-archive

5247
1

efe0222130 · media : add SVG logo [no ci] · Updated 2025-03-27 16:07:46 -05:00    upstream-archive

5250
1

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

5278
8

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

5271
2

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

5283
2

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

5276
1