Default Branch

9ba399dfa7 · server : add support for "encoding_format": "base64" to the */embeddings endpoints (#10967) · Updated 2024-12-24 21:33:04 +01:00

Branches

65f9293d14 · devops : remove clblast + LLAMA_CUDA -> GGML_CUDA · Updated 2024-06-26 18:17:26 +02:00

1155
1

1e6e363d7f · test zero max buffer size · Updated 2024-06-26 17:11:09 +02:00

1156
1

ff0aa3abd1 · fix part of mul_mat_id · Updated 2024-06-21 05:38:00 +02:00

1199
1

f3974cabac · all matrix multiplication backend · Updated 2024-06-18 13:18:26 +02:00

1240
1

ce6e28cc23 · Update ggml-sycl.cpp · Updated 2024-06-18 10:57:14 +02:00

1251
6

ef79941ac9 · llama : disable FA if KV head size do not match · Updated 2024-06-17 18:20:24 +02:00

1221
1

a235b7c532 · Vectorize q load · Updated 2024-06-17 11:30:40 +02:00

1251
11

98f948b9d0 · unicode : avoid char32_t · Updated 2024-06-16 12:18:46 +02:00

1236
1

28f7a4d028 · ggml : fix handling of zero blocks in IQ quants · Updated 2024-06-16 09:41:53 +02:00

1237
1

e9f2abfc8c · bitnet : pad tensors to 256 · Updated 2024-06-15 18:01:03 +02:00

1255
25

34bdbed481 · rpc : fix load/store misaligned addresses · Updated 2024-06-15 13:39:20 +02:00

1239
1

eaf34ba0cd · metal : utilize max shared memory for mul_mat_id · Updated 2024-06-14 12:02:25 +02:00

1246
1

18133cab40 · Revert "use the correct SYCL context for host USM allocations" · Updated 2024-06-13 13:08:27 +02:00

1251
4

46325233c9 · Revert 7777 · Updated 2024-06-12 17:22:55 +02:00

1251
1

8412561c4b · ggml : update unary asserts and "supports_op" · Updated 2024-06-12 14:25:14 +02:00

1252
2

cd026b48ef · ggml : support more contiguous cases · Updated 2024-06-12 14:12:32 +02:00

1267
2

4356325ef5 · tests : check the Python version · Updated 2024-06-11 08:05:15 +02:00

1263
1

4bb03cade0 · ci : disable server-windows workflow · Updated 2024-06-10 11:30:18 +02:00

1272
1

9e4d62e6ab · server : improve "prompt" handling · Updated 2024-06-10 08:31:50 +02:00

1272
1

956bb14595 · examples : remove --instruct remnants · Updated 2024-06-10 07:37:47 +02:00

1272
1