furyhawk/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-21 18:25:57 +00:00
Code Issues Packages Projects Releases Wiki Activity
10,083 Commits 618 Branches 6,871 Tags

Default Branch

master

846e991ec3 · cuda: add sqrt_softplus in topk-moe for dsv4 (#25896) · Updated 2026-07-21 16:30:01 +00:00
 ZIP  TAR.GZ

Branches

gg/per-layer-kv

fc5f334689 · readme : add API change notice · Updated 2023-12-07 10:35:02 +00:00    furyhawk

8465
15
 ZIP  TAR.GZ
gg/quantum-k-cache

af99c6fbfc · llama : remove memory_f16 and kv_f16 flags · Updated 2023-12-05 16:18:16 +00:00    furyhawk

8477
26
 ZIP  TAR.GZ
gg/pad-kv-cache

3cb1c348b3 · metal : try to improve batched decoding · Updated 2023-12-01 20:01:58 +00:00    furyhawk

8482
2
 ZIP  TAR.GZ
gg/soft-max-ext

eb594c0f7d · alloc : fix build with debug · Updated 2023-12-01 08:46:05 +00:00    furyhawk

8506
14
 ZIP  TAR.GZ
ceb/libstdcpp-assertions

5b74310e6e · build : enable libstdc++ assertions for debug builds · Updated 2023-11-30 23:18:24 +00:00    furyhawk

8491
1
 ZIP  TAR.GZ
assert-restore-abort

bb39b87964 · ggml : restore abort() in GGML_ASSERT · Updated 2023-11-28 00:27:09 +00:00    furyhawk

8510
1
 ZIP  TAR.GZ
gg/fix-cpu-blas

87f4102a70 · llama : revert n_threads_batch logic · Updated 2023-11-27 19:47:35 +00:00    furyhawk

8511
3
 ZIP  TAR.GZ
ceb/perf-faster-multigpu

6272b6764a · use stride=128 if built for tensor cores · Updated 2023-11-27 18:09:14 +00:00    furyhawk

8514
3
 ZIP  TAR.GZ
lookahead

8d8b76d469 · lookahead : add comments · Updated 2023-11-26 09:26:55 +00:00    furyhawk

8526
9
 ZIP  TAR.GZ
server-oai-compat

21b70babf7 · straightforward /v1/models endpoint · Updated 2023-11-24 16:22:39 +00:00    furyhawk

8527
12
 ZIP  TAR.GZ
kv-cache-opts

f8e9f11428 · common : add -dkvc arg for enabling kv cache dumps · Updated 2023-11-23 16:47:56 +00:00    furyhawk

8533
4
 ZIP  TAR.GZ
ceb/fix-yarn-neox

f824902623 · YaRN : correction to GPT-NeoX implementation · Updated 2023-11-15 22:10:52 +00:00    furyhawk

8565
1
 ZIP  TAR.GZ
llama-metadata

d0445a2eff · better documentation · Updated 2023-11-10 00:38:20 +00:00    furyhawk

8582
3
 ZIP  TAR.GZ
fix-tensor-split-zero

47d604fa2d · fix issues · Updated 2023-11-05 12:20:22 +00:00    furyhawk

8596
3
 ZIP  TAR.GZ
revert-pool

3ef358fffd · Revert "cuda : use CUDA memory pool with async memory allocation/deallocation when available (#3903)" · Updated 2023-11-04 20:26:51 +00:00    furyhawk

8600
2
 ZIP  TAR.GZ
metal-soft-max

46868a499e · metal : multi-simd softmax · Updated 2023-11-01 19:16:34 +00:00    furyhawk

8625
1
 ZIP  TAR.GZ
llm-build-context

a8796f9609 · llm : cleanup + comments · Updated 2023-11-01 18:08:02 +00:00    furyhawk

8634
4
 ZIP  TAR.GZ
llm-reuse-constants

7420bef83e · wip wip wip · Updated 2023-11-01 06:51:43 +00:00    furyhawk

8634
1
 ZIP  TAR.GZ
llama-refactor

afb3929279 · Merge branch 'master' into llama-refactor · Updated 2023-10-31 18:35:31 +00:00    furyhawk

8636
21
 ZIP  TAR.GZ
test-mmv

29fe516913 · wip · Updated 2023-10-31 16:36:37 +00:00    furyhawk

8637
1
 ZIP  TAR.GZ