Default Branch

b97ebdc98f · llama-quant : fix --tensor-type when default qtype is overriden (#22572) · Updated 2026-05-01 17:55:55 +00:00

Branches

0fca4308f7 · Initial plan · Updated 2026-01-08 15:16:59 +00:00    sdgoij

1325
2

091d98e2c5 · rpc : use std::unique_ptr for the message_queue · Updated 2026-01-06 13:32:01 +00:00    sdgoij

1364
2

54ccf2476b · ci : require editor config · Updated 2026-01-06 11:04:35 +00:00    sdgoij

1356
1

4a95b44864 · alloc : skip unassigned leafs · Updated 2026-01-06 09:24:56 +00:00    sdgoij

1356
1

bf3f12df4c · graph : constant topology for tokens/embeddings inputs · Updated 2026-01-02 13:46:45 +00:00    sdgoij

1389
2

6ecba0d0d0 · fix 5 · Updated 2025-12-30 12:53:52 +00:00    sdgoij

1422
170

42c40819ca · handle case done === 0 · Updated 2025-12-29 20:07:10 +00:00    sdgoij

1423
2

eaa639af65 · update · Updated 2025-12-29 11:41:48 +00:00    sdgoij

1457
17

3b54531ead · ci : disable mmap · Updated 2025-12-28 07:26:51 +00:00    sdgoij

1443
1

5f14aa8e43 · gguf-py : do not align the data start offset · Updated 2025-12-22 14:49:54 +00:00    sdgoij

1498
1

a95df75322 · add test model · Updated 2025-12-18 22:44:01 +00:00    sdgoij

1562
13

6b1394ed74 · prof: fix tensor dims formatter · Updated 2025-12-18 01:11:21 +00:00    sdgoij

1535
3

e47a082fc9 · security : add collaborator guidance · Updated 2025-12-16 08:16:46 +00:00    sdgoij

1576
1

4574ab6f40 · preset: handle negated arg, reverse the meaning if needed · Updated 2025-12-14 20:44:41 +00:00    sdgoij

1596
1

357f999381 · graph: add f_attn_temp_offset · Updated 2025-12-14 11:12:12 +00:00    sdgoij

1600
1

292f8e231c · model-conversion : cast logits to float32 · Updated 2025-12-13 20:24:21 +00:00    sdgoij

1612
1

2a615b27e4 · ggml : remove redundant src in ggml_cast · Updated 2025-12-09 09:16:15 +00:00    sdgoij

1669
1

31436df5ae · contrib : stale PRs · Updated 2025-12-05 20:49:15 +00:00    sdgoij

1709
1

dad7571ff2 · tests : better input range for unary operators · Updated 2025-12-04 10:18:24 +00:00    sdgoij

1733
1

01c9e9fd5c · llama : fix sanity checks during quantization · Updated 2025-12-03 09:10:11 +00:00    sdgoij

1753
1