index
:
ik_llama.cpp.git
main
Unnamed repository; edit this file 'description' to name the repository.
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
src
Age
Commit message (
Expand
)
Author
2024-10-20
Avoid rebuild of GGML graph for each token (#98)
agray3
2024-10-19
Bitnet: make the scale tensors optional (#97)
Kawrakow
2024-10-19
Quant strategies: attn_q Q4 & attn_v Q6 for Llama 3.1 Q5_K_S (#96)
Nexes the Elder
2024-10-18
CLI - Specify GGML_TYPE to quantize for the main tensors. (#91)
Nexes the Elder
2024-10-16
Adding IQ4_KSS: 4.0 bpw quants (#89)
Kawrakow
2024-10-13
IQ2_KS: 2.1875 bpw non-linear quantization (#85)
Kawrakow
2024-10-11
Minor: printf -> LLAMA_LOG_INFO
Iwan Kawrakow
2024-10-10
Better model info (#84)
Kawrakow
2024-10-09
New SOTA quantization: 4.25 bpw IQ4_KS (#83)
Kawrakow
2024-10-02
Fused unary(x)*y (#70)
Kawrakow
2024-10-02
Adding Q6_0 (#77)
Kawrakow
2024-09-29
Allow bf16 kv-cache (#69)
Kawrakow
2024-09-28
Time to fix replace_all (#68)
Kawrakow
2024-09-28
CUDA non-contiguous RoPE (#66)
Kawrakow
2024-09-28
Adding SWIGLU unary op (#65)
Kawrakow
2024-09-28
Better sub-3-bit quantization mixes with a qkv tensor (#64)
Kawrakow
2024-09-27
Adding ability to have meta data per tensor row (#61)
Kawrakow
2024-09-19
Minor
Iwan Kawrakow
2024-09-14
Quantization mixes tweaks (#53)
Kawrakow
2024-09-09
Adding IQ1_TN - 1.6875 bpw for TriLM ternary models (#44)
Kawrakow
2024-09-08
Adding fused rms_norm (#42)
Kawrakow
2024-08-27
Faster Gemma2 (#27)
Kawrakow
2024-08-21
softcap: minor improvement (#24)
Kawrakow
2024-08-20
Fused soft cap and SIMD-ified GeLU (#9)
Kawrakow
2024-08-20
iq4_k: use iq5_k also when n_gqa = 2 (#23)
Kawrakow
2024-08-19
iq2_k: slightly better bpw - accuracy compromise (#20)
Kawrakow
2024-08-12
Merge mainline - Aug 12 2024 (#17)
Kawrakow
2024-08-09
iq6_k: WIP (quantize/dequantize)
Iwan Kawrakow
2024-08-07
Adding IQ2_TN for use with ternary models (#13)
Kawrakow
2024-08-05
q2_K: allow it to detect ternary nets and quantize accordingly
Iwan Kawrakow
2024-08-01
iq3_k: Basics
Iwan Kawrakow
2024-08-01
iq5_k: Basics
Iwan Kawrakow
2024-08-01
iq2_k: Basics
Iwan Kawrakow
2024-07-28
IQ4_K: SOTA 4-bit quantization (#6)
Kawrakow
2024-07-27
Merge mainline llama.cpp (#3)
Kawrakow
[prev]