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
/
ggml
/
include
Age
Commit message (
Expand
)
Author
2025-06-08
Fix non rpc build error (#506)
firecoperana
2025-06-08
Revert "Rpc improvement (#480)"
Iwan Kawrakow
2025-06-08
Rpc improvement (#480)
firecoperana
2025-05-23
Trellis quants with CPU inference (#441)
Andrew Chan
2025-05-20
Bug fixes from mainline (#439)
Kawrakow
2025-05-17
IQ5_KS_R4: row-interleaved IQ5_KS (#426)
Kawrakow
2025-05-15
Adding IQ5_KS - 5.25 bpw quants (#422)
Kawrakow
2025-05-12
GPU offload policy (#405)
Kawrakow
2025-04-07
Add copyright notices (#317)
Kawrakow
2025-03-27
Use bf16 instead of fp16 block scales for q8_1 (#292)
Kawrakow
2025-03-02
SER - Smart Expert Reduction (#239)
Kawrakow
2025-02-23
Fused MoE ffn_up and ffn_gate (#229)
Kawrakow
2025-02-19
Q8_KV: 8-bit quantization type targeting the KV cache (#208)
Kawrakow
2025-02-09
Use Q8_K_128 for IQ1_S_R4 and IQ1_M_R4 matrix multiplications (#194)
Kawrakow
2025-02-08
Revert #79 (#192)
Kawrakow
2025-02-06
Rename q4_0_r4, q8_0_r4 and iq4_xs_r4 to _r8 (#189)
Kawrakow
2025-02-06
IQ1_M_R4: better 1.75 bpw quants (#187)
Kawrakow
2025-02-05
IQ1_S_R4: better 1.5 bpw quants (#185)
Kawrakow
2025-01-15
CPU Flash Attention improvements (#172)
Kawrakow
2025-01-10
Be able to re-quantize MS BitNet I2_S models (#169)
Kawrakow
2024-12-23
IQ3_S_R4 (#162)
Kawrakow
2024-12-21
IQ2_S_R4 (#156)
Kawrakow
2024-12-21
IQ2_XS_R4 (#155)
Kawrakow
2024-12-20
IQ2_XXS_R4 (#154)
Kawrakow
2024-12-20
IQ3_XXS_R4 (#153)
Kawrakow
2024-12-18
IQ4_KS_R4 (#150)
Kawrakow
2024-12-18
IQ5_K_R4 (#149)
Kawrakow
2024-12-17
IQ2_K_R4 (#146)
Kawrakow
2024-12-17
IQ3_K_R4 (#145)
Kawrakow
2024-12-15
BF16_R16 - 16 interleaved bf16 rows (#142)
Kawrakow
2024-12-14
Q8_K_R8: Fastest quantized matrix multiplications (#141)
Kawrakow
2024-12-12
IQ4_K_R4 (#138)
Kawrakow
2024-12-11
Q2_K_R4 (#136)
Kawrakow
2024-12-11
Q3_K_R4 (#134)
Kawrakow
2024-12-10
Q5_K_R4 (#132)
Kawrakow
2024-12-10
Q6_K_R4 (#130)
Kawrakow
2024-12-09
Q4_K_R4 (#129)
Kawrakow
2024-12-08
Faster IQ4_XS_R4 on Zen4 (#128)
Kawrakow
2024-12-08
Rename iq4_nl_x4 to iq4_nl_r4 (#126)
Kawrakow
2024-12-06
iq2_bn_r4: fastest Bitnet CPU implementation on the planet (#124)
Kawrakow
2024-12-04
IQ4_XS_R4 (#123)
Kawrakow
2024-12-03
Q5_0_R4 (#121)
Kawrakow
2024-12-03
Q8_0_R4 (#120)
Kawrakow
2024-12-02
Q4_0_R4 (#119)
Kawrakow
2024-12-02
IQ4_NL_X4 (#118)
Kawrakow
2024-10-31
Faster MoE inference (#112)
Kawrakow
2024-10-25
Remove forgotten IQ1_TN, IQ2_TN enum values
Iwan Kawrakow
2024-10-25
Bitnet changes (#106)
Kawrakow
2024-10-20
Avoid rebuild of GGML graph for each token (#98)
agray3
2024-10-16
Adding IQ4_KSS: 4.0 bpw quants (#89)
Kawrakow
[next]