Skip to content
GitLab
Explore
Sign in
Overview
Active
Stale
All
This project is mirrored from
https://github.com/ggerganov/llama.cpp
. Pull mirroring updated
Sep 20, 2024
.
gg/spm-fix
f35acb84
·
swift : pin ggml commit + remove ggml.h from spm-headers
·
Jan 11, 2024
ik/iq2_2.31bpw
9bfcb16f
·
Add llama enum for IQ2_XS
·
Jan 11, 2024
ik/restore_k-quants_for_MoE
31fb4d8e
·
Merge branch 'master' into ik/restore_k-quants_for_MoE
·
Jan 11, 2024
gg/llama-fix-k-shift-n-rot
0cb764e4
·
llama : always use hparams.n_rot for ggml_rope_custom
·
Jan 12, 2024
gg/metal-feature-set
5d33d3cd
·
Merge branch 'master' into gg/metal-feature-set
·
Jan 12, 2024
ik/quantize-iq2
f342143e
·
imatrix: guard even more against low-bit quantization misuse
·
Jan 12, 2024
ik/MoE_quant_mix
f5205f85
·
Make Q3_K_S be the same as olf Q3_K_L for Mixtral-8x7B
·
Jan 13, 2024
gg/update-phi2-convert
1fb563eb
·
py : try to fix flake stuff
·
Jan 13, 2024
gg/add-phixtral
9998ecd1
·
llama : add phixtral support (wip)
·
Jan 13, 2024
gg/server-system-cache-4902
9ec53ba0
·
server : fix prompt caching with system prompt
·
Jan 13, 2024
gg/fix-detokenization-added-tokens
f6185f9b
·
Fix detokenization of non-special added-tokens
·
Jan 13, 2024
sl/micro-batching
40b3c5ef
·
pipeline parallelism demo
·
Jan 13, 2024
gg/metal-rm-api
96cf0282
·
metal : remove old API
·
Jan 13, 2024
ik/fix_qxm_moe
121eb066
·
Fix the fix
·
Jan 14, 2024
gg/llama-trace
0abbe2fc
·
llama : check LLAMA_TRACE env for extra logging
·
Jan 14, 2024
ik/imatrix_k_quants
90096a5f
·
Add ability to use importance matrix for all k-quants
·
Jan 14, 2024
ik/cuda_faster_legacy_dequantize
08b89f7e
·
CUDA: faster dequantize kernels for Q4_0 and Q4_1
·
Jan 14, 2024
ik/quantize_iq2_notcompatible
dccaec76
·
The check for 256 divisibility was missing for IQ2_XS, IQ2_XXS
·
Jan 15, 2024
gg/sched-eval-callback-4931
40cdb397
·
backend : clean-up the implementation
·
Jan 15, 2024
crasm_segfault-on-pthread
e6e34b2a
·
add test to tests/CMakeLists.txt
·
Jan 15, 2024
Prev
1
…
13
14
15
16
17
18
19
20
21
…
26
Next