upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-01 02:17:42 -05:00
Code Issues Packages Projects Releases Wiki Activity
11,323 Commits 825 Branches 7,693 Tags

Default Branch

master

f11d642a27 · HIP: avoid treating CDNA as dgx spark for gqa_ratio 20 in fattn_mma dqk 576 (#29572) · Updated 2026-10-01 00:51:38 -05:00
 ZIP  TAR.GZ

Branches

gg/metal-fa-f16

a2385da59c · make : clean-up [no ci] · Updated 2024-11-08 05:46:20 -06:00    upstream-archive

7274
9
 ZIP  TAR.GZ
gg/metal-fa-f16-save

94accca4c2 · vec move mask to shmem · Updated 2024-11-07 12:58:10 -06:00    upstream-archive

7284
19
 ZIP  TAR.GZ
fix_sycl_ci

c5d8bb5a81 · leave only basic functions for SYCL CI · Updated 2024-11-06 01:47:50 -06:00    upstream-archive

7349
2
 ZIP  TAR.GZ
sl/llama-bench-headers

4fc8673d09 · llama-bench : skip repeated values in consecutive lines · Updated 2024-11-02 09:37:33 -05:00    upstream-archive

7309
1
 ZIP  TAR.GZ
sl/aligned-alloc-no-abort

20e12112fd · llama : suggest reduce ctx size when kv init fails · Updated 2024-11-01 18:55:19 -05:00    upstream-archive

7312
2
 ZIP  TAR.GZ
sl/auto-flash-attn

afc4a7de65 · llama : enable flash attn automatically when supported · Updated 2024-10-30 17:30:06 -05:00    upstream-archive

7329
1
 ZIP  TAR.GZ
support_device_reg

8233009d4d · Support SYCL device register · Updated 2024-10-19 21:06:51 -05:00    upstream-archive

7410
1
 ZIP  TAR.GZ
gg/ttfb

bc82fc2ed8 · llama-bench : add time-to-first-byte stat · Updated 2024-10-18 08:40:02 -05:00    upstream-archive

7381
1
 ZIP  TAR.GZ
pr_add_intel_amx_support

2d3fc54ac6 · add amx kernel for gemm · Updated 2024-10-17 22:35:49 -05:00    upstream-archive

7391
1
 ZIP  TAR.GZ
sl/fix-sched-reserve

630bce5a7f · ggml : fix possible buffer use after free in sched reserve · Updated 2024-10-17 17:21:54 -05:00    upstream-archive

7389
1
 ZIP  TAR.GZ
gg/grammar-refactor

17b3a3e8cc · llama : minor llama_grammar refactoring · Updated 2024-10-17 04:23:27 -05:00    upstream-archive

7417
4
 ZIP  TAR.GZ
compilade/pyright-fix-ignores

a34fc0dd86 · ci : reduce severity of unused Pyright ignore comments · Updated 2024-09-30 12:59:40 -05:00    upstream-archive

7472
1
 ZIP  TAR.GZ
gg/tfs-ob1

114ab6347e · sampling : fix off-by-one in tail-free sampling · Updated 2024-09-23 03:44:55 -05:00    upstream-archive

7516
1
 ZIP  TAR.GZ
gg/tokenizer-cleanup

6e873e561a · llama : make llm_tokenizer more private · Updated 2024-09-20 03:41:51 -05:00    upstream-archive

7535
2
 ZIP  TAR.GZ
sl/fix-omp-one-thread

6b0248c29a · Update ggml/src/ggml.c · Updated 2024-09-18 11:00:26 -05:00    upstream-archive

7540
2
 ZIP  TAR.GZ
fix_ctx_default

a6a8f8d09c · Update docs/backend/SYCL.md · Updated 2024-09-17 03:25:43 -05:00    upstream-archive

7572
2
 ZIP  TAR.GZ
gg/cb-naming

cc1c017191 · naming : normalize the name of callback-related identifiers · Updated 2024-09-16 01:11:42 -05:00    upstream-archive

7560
1
 ZIP  TAR.GZ
sycl-cmake-append

73ef3f769c · Update llama-server-intel.Dockerfile · Updated 2024-09-15 10:21:46 -05:00    upstream-archive

7565
3
 ZIP  TAR.GZ
gg/cmake-dedup-link

fb8f142554 · one more CMAKE_CXX_FLAGS fix (#9471) · Updated 2024-09-13 08:13:07 -05:00    upstream-archive

7574
5
 ZIP  TAR.GZ
gg/ggml-atomic-int

d7c042d1ae · ggml : make n_threads_cur atomic_int · Updated 2024-09-11 13:12:11 -05:00    upstream-archive

7590
1
 ZIP  TAR.GZ