ggml-org/llama.cpp
0
0 Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-22 17:49:50 +08:00
Code Issues Packages Projects Releases Wiki Activity
11,815 Commits 884 Branches 8,116 Tags

Default Branch

master

7170cad4d0 · sycl: fix CONV_2D wrong results for non-contiguous input (#30363) · Updated 2026-10-22 16:19:58 +08:00
 ZIP  TAR.GZ

Branches

gg/indent

f55b647300 · llama : minor indentation during tensor loading · Updated 2024-07-05 00:34:04 +08:00    tqcq

8067
16
 ZIP  TAR.GZ
sl/fix-ppl-seq-max

dcab343f2f · use 1 seq for kl_divergence · Updated 2024-07-03 22:22:58 +08:00    tqcq

8082
2
 ZIP  TAR.GZ
fairydreaming/t5-clean-3-gg

703764a382 · convert : use non-fast T5 tokenizer · Updated 2024-07-03 00:29:26 +08:00    tqcq

8124
10
 ZIP  TAR.GZ
gg/nix-remove-opencl

d4a1923d4e · minor : remove parentheses · Updated 2024-07-01 19:45:55 +08:00    tqcq

8102
2
 ZIP  TAR.GZ
add-gemma2-soft-capping

51f0bd50a1 · Remove custom pre attention scaling and use computed value instead. · Updated 2024-06-30 11:02:50 +08:00    tqcq

8105
10
 ZIP  TAR.GZ
codeplay/tg-warmup

712e4d9450 · Generate full token count during warm up · Updated 2024-06-28 20:29:00 +08:00    tqcq

8108
1
 ZIP  TAR.GZ
gg/fix-devops

65f9293d14 · devops : remove clblast + LLAMA_CUDA -> GGML_CUDA · Updated 2024-06-27 00:17:26 +08:00    tqcq

8134
1
 ZIP  TAR.GZ
sl/zero-max-size

1e6e363d7f · test zero max buffer size · Updated 2024-06-26 23:11:09 +08:00    tqcq

8135
1
 ZIP  TAR.GZ
sycl-mul-mat-id

ff0aa3abd1 · fix part of mul_mat_id · Updated 2024-06-21 11:38:00 +08:00    tqcq

8178
1
 ZIP  TAR.GZ
sl/test-mul-mat-backend

f3974cabac · all matrix multiplication backend · Updated 2024-06-18 19:18:26 +08:00    tqcq

8219
1
 ZIP  TAR.GZ
codeplay/fix-matmul-arith

ce6e28cc23 · Update ggml-sycl.cpp · Updated 2024-06-18 16:57:14 +08:00    tqcq

8230
6
 ZIP  TAR.GZ
gg/fa-req-kq-hs

ef79941ac9 · llama : disable FA if KV head size do not match · Updated 2024-06-18 00:20:24 +08:00    tqcq

8200
1
 ZIP  TAR.GZ
codeplay/dequant_q4_K_improvements

a235b7c532 · Vectorize q load · Updated 2024-06-17 17:30:40 +08:00    tqcq

8230
11
 ZIP  TAR.GZ
gg/no-char32_t

98f948b9d0 · unicode : avoid char32_t · Updated 2024-06-16 18:18:46 +08:00    tqcq

8214
1
 ZIP  TAR.GZ
gg/ggml-fix-zero-blocks

28f7a4d028 · ggml : fix handling of zero blocks in IQ quants · Updated 2024-06-16 15:41:53 +08:00    tqcq

8215
1
 ZIP  TAR.GZ
gg/bitnet

e9f2abfc8c · bitnet : pad tensors to 256 · Updated 2024-06-16 00:01:03 +08:00    tqcq

8209
25
 ZIP  TAR.GZ
gg/rpc-fix-misaligned

34bdbed481 · rpc : fix load/store misaligned addresses · Updated 2024-06-15 19:39:20 +08:00    tqcq

8193
1
 ZIP  TAR.GZ
gg/metal-mmid-max-rows

eaf34ba0cd · metal : utilize max shared memory for mul_mat_id · Updated 2024-06-14 18:02:25 +08:00    tqcq

8200
1
 ZIP  TAR.GZ
codeplay/revert-host-alloc

18133cab40 · Revert "use the correct SYCL context for host USM allocations" · Updated 2024-06-13 19:08:27 +08:00    tqcq

8205
4
 ZIP  TAR.GZ
revert-7777-host-usm-context-fix

46325233c9 · Revert 7777 · Updated 2024-06-12 23:22:55 +08:00    tqcq

8205
1
 ZIP  TAR.GZ