upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-01 15:40:46 -05:00
Code Issues Packages Projects Releases Wiki Activity
10,222 Commits 643 Branches 6,961 Tags

Default Branch

master

a7a6d0d269 · vulkan: extend topk_moe fusion to support sqrt(softplus) (#26124) · Updated 2026-08-01 14:18:07 -05:00
 ZIP  TAR.GZ

Branches

metal-soft-max

46868a499e · metal : multi-simd softmax · Updated 2023-11-01 14:16:34 -05:00    upstream-archive

8764
1
 ZIP  TAR.GZ
llm-build-context

a8796f9609 · llm : cleanup + comments · Updated 2023-11-01 13:08:02 -05:00    upstream-archive

8773
4
 ZIP  TAR.GZ
llm-reuse-constants

7420bef83e · wip wip wip · Updated 2023-11-01 01:51:43 -05:00    upstream-archive

8773
1
 ZIP  TAR.GZ
llama-refactor

afb3929279 · Merge branch 'master' into llama-refactor · Updated 2023-10-31 13:35:31 -05:00    upstream-archive

8775
21
 ZIP  TAR.GZ
test-mmv

29fe516913 · wip · Updated 2023-10-31 11:36:37 -05:00    upstream-archive

8776
1
 ZIP  TAR.GZ
deploy

dab42893c9 · scripts : working curl pipe · Updated 2023-10-31 10:03:56 -05:00    upstream-archive

8776
3
 ZIP  TAR.GZ
llama-refactor-norm

7923b70cb8 · llama : add llm_build_inp_embd helper · Updated 2023-10-31 09:43:08 -05:00    upstream-archive

8781
37
 ZIP  TAR.GZ
ggml-impl

4b3cb98d46 · ggml-impl : move extern "C" to start of file · Updated 2023-10-30 12:05:58 -05:00    upstream-archive

8777
7
 ZIP  TAR.GZ
lto

bc28aaa8c2 · make : use -lfto=auto to avoid warnings and maintain perf · Updated 2023-10-30 09:00:53 -05:00    upstream-archive

8777
5
 ZIP  TAR.GZ
scratch

15267192c0 · llama : refactor tensor offloading as callback · Updated 2023-10-29 06:04:36 -05:00    upstream-archive

8781
15
 ZIP  TAR.GZ
ggml-quants

8a86b95e87 · quantize : --pure option for disabling k-quant mixtures · Updated 2023-10-28 15:37:03 -05:00    upstream-archive

8782
3
 ZIP  TAR.GZ
apply-3585

de7e0912b6 · convert : ignore tokens if their IDs are within [0, vocab_size) · Updated 2023-10-28 07:01:36 -05:00    upstream-archive

8785
1
 ZIP  TAR.GZ
sampling-greedy-with-probs

bbfc62ac2f · sampling : temp == 0.0 -> no probs, temp < 0.0 -> probs · Updated 2023-10-28 06:04:57 -05:00    upstream-archive

8793
3
 ZIP  TAR.GZ
cuda-multi-gpu

cd3e20fb50 · cuda : fix multi-gpu with tensor cores · Updated 2023-10-27 15:11:50 -05:00    upstream-archive

8792
3
 ZIP  TAR.GZ
cuda-quantum-batch

49af767fad · build : add compile option to force use of MMQ kernels · Updated 2023-10-27 05:21:04 -05:00    upstream-archive

8794
7
 ZIP  TAR.GZ
cuda-batched-gemm

d798a17c34 · cuda : add TODO for calling cublas from kernel + using mem pool · Updated 2023-10-24 08:33:24 -05:00    upstream-archive

8808
10
 ZIP  TAR.GZ
cuda-batched-gemm-deq

6966474928 · cuda : play with faster Q4_0 dequantization · Updated 2023-10-24 02:29:40 -05:00    upstream-archive

8808
8
 ZIP  TAR.GZ
upd-issue-templates

b9bb4cbe86 · Separate bug and enhancement template + no default title · Updated 2023-10-23 10:59:11 -05:00    upstream-archive

8808
1
 ZIP  TAR.GZ
server-rev

c0f4d54870 · server : add comment about changing slot_state to bool · Updated 2023-10-22 14:24:39 -05:00    upstream-archive

8814
72
 ZIP  TAR.GZ
perf-study

cb79f8a2d8 · llama : add SKIP_KQ_KQV option · Updated 2023-10-22 01:58:29 -05:00    upstream-archive

8814
3
 ZIP  TAR.GZ