Default branch

d7b31a9d84 · sync: minja (a72057e519) (#11774) · Updated 2025-02-10 09:34:09 +00:00

Branches

712e4d9450 · Generate full token count during warm up · Updated 2024-06-28 12:29:00 +00:00    vbatts

1419
1

65f9293d14 · devops : remove clblast + LLAMA_CUDA -> GGML_CUDA · Updated 2024-06-26 16:17:26 +00:00    vbatts

1445
1

1e6e363d7f · test zero max buffer size · Updated 2024-06-26 15:11:09 +00:00    vbatts

1446
1

ff0aa3abd1 · fix part of mul_mat_id · Updated 2024-06-21 03:38:00 +00:00    vbatts

1489
1

f3974cabac · all matrix multiplication backend · Updated 2024-06-18 11:18:26 +00:00    vbatts

1530
1

ce6e28cc23 · Update ggml-sycl.cpp · Updated 2024-06-18 08:57:14 +00:00    vbatts

1541
6

ef79941ac9 · llama : disable FA if KV head size do not match · Updated 2024-06-17 16:20:24 +00:00    vbatts

1511
1

a235b7c532 · Vectorize q load · Updated 2024-06-17 09:30:40 +00:00    vbatts

1541
11

98f948b9d0 · unicode : avoid char32_t · Updated 2024-06-16 10:18:46 +00:00    vbatts

1526
1

28f7a4d028 · ggml : fix handling of zero blocks in IQ quants · Updated 2024-06-16 07:41:53 +00:00    vbatts

1527
1

e9f2abfc8c · bitnet : pad tensors to 256 · Updated 2024-06-15 16:01:03 +00:00    vbatts

1545
25

34bdbed481 · rpc : fix load/store misaligned addresses · Updated 2024-06-15 11:39:20 +00:00    vbatts

1529
1

eaf34ba0cd · metal : utilize max shared memory for mul_mat_id · Updated 2024-06-14 10:02:25 +00:00    vbatts

1536
1

18133cab40 · Revert "use the correct SYCL context for host USM allocations" · Updated 2024-06-13 11:08:27 +00:00    vbatts

1541
4

46325233c9 · Revert 7777 · Updated 2024-06-12 15:22:55 +00:00    vbatts

1541
1

8412561c4b · ggml : update unary asserts and "supports_op" · Updated 2024-06-12 12:25:14 +00:00    vbatts

1542
2

cd026b48ef · ggml : support more contiguous cases · Updated 2024-06-12 12:12:32 +00:00    vbatts

1557
2

4356325ef5 · tests : check the Python version · Updated 2024-06-11 06:05:15 +00:00    vbatts

1553
1

4bb03cade0 · ci : disable server-windows workflow · Updated 2024-06-10 09:30:18 +00:00    vbatts

1562
1

9e4d62e6ab · server : improve "prompt" handling · Updated 2024-06-10 06:31:50 +00:00    vbatts

1562
1