FazBrowse GitHub Viewer | Trending | | Home

Tools: [Download Repo ZIP] [Original HTTPS Page]

Commits · allozaur/llama.cpp · GitHub

Commits

Commits on Aug 5, 2026

build : remove GGML_METAL_USE_BF16 from all build scripts (#26604)
nikwen
authored
d52ec04
ui: Update vulnerable packages + cleanup Storybook config (#26607)
allozaur
authored
e031d95

Commits on Aug 4, 2026

Prefer npm ci over install for security (#26601)
eapache
authored
6ea215d
server: decode Windows OEM output to UTF-8 in built-in tools (#26597)
ServeurpersoCom
authored
4308a4f
mtmd: correcting duplicate empty audio chunks for short inputs (#26536)
Abhinaykrishna2
authored
474c92e
sampler : remove "full-context windows" from history-based samplers (#26524)
ggerganov
authored
a6aa6f5
gguf-split: Add option to delete split parts during merge (#26538)

guiq83
and
CISC
authored
76c956c
ui: CWD for agent (#26518)

allozaur
and
ServeurpersoCom
authored
2f56fc3
mtmd: support Qwen3-TTS (note: breaking change to llama-tts binary) (#26254)

ngxson
and
ServeurpersoCom
authored
0713275
models : fix dflash wo_a reshape on load (#26577)
ggerganov
authored
1c3c967
ci: fix pre-built binaries no longer working on macOS 15 and below (#26375)
nikwen
authored
6b5224c
speculative : refactor enabled configs common_speculative_init (#26510)
danbev
authored
7bd8282
gguf-py: validate n_dims and guard against uint64 overflow in reader (#25401)
hclsys
authored
5788b51
sync : ggml
ggerganov
committed
2e17f69
ggml : bump version to 0.18.1 (ggml/1578)
ggerganov
committed
15831f5
convert : add missing return after setting tekken vocab (#25947)
AngelGalindo7
authored
b5746d2
vulkan backend ops: implemented GATED_LINEAR_ATTN (#25601)
PranavUttarkar
authored
f26efa0
vocab : validate plamo2 byte tokens (#26511)
CISC
authored
cf06ad7
convert : import bytes_to_unicode from convert_slow_tokenizer (#26217)
SolshineCode
authored
b06fbc9
model : allow reshape of tensors during load (#26531)
ggerganov
authored
1269cb1
llama : move n_vocab from llama_sampler_data to penalty_sampler (#26520)
ggerganov
authored
935cad6
ci: fix vulkan llvmpipe runs (#26533)
netrunnereve
authored
22dc605
sycl: parallelize the non-contiguous concat kernel (#25852)
Titaniumtown
authored
6c8dcaa
Extended SYCL oneDNN SDPA to non-FP16 KV caches (Q4_0–Q8_0 and FP32) (#25874)

johnkarlhill
and
claude
authored
66fa168

Commits on Aug 3, 2026

chat : add new template for DeepSeek V4 Flash 0731 (#26398)
tarruda
authored
0ef6e55
vendor : update cpp-httplib to 0.52.0 (#26485)
cabelo
authored
94bc47f
vendor : update BoringSSL to 0.20260803.0 (#26523)
cabelo
authored
fe2adf0
model : support MTP in GLM-4.7-Flash (#24868)
jacekpoplawski
authored
57c0921
tests: add model resolution test on synthetic repo listings (#26172)

ServeurpersoCom
and
ngxson
authored
ee0445c
server: add get_info tool (#26522)

ngxson
and
ServeurpersoCom
authored
99111b1
vocab : validate default special token ids (#26506)
CISC
authored
e8e06f7
ggml: use dynamic allocation for split graph inputs (#22789)

AgoraPete
and
ggerganov
authored
dbadb68
opencl: route large q6_K lm_head to the flat GEMV (#26427)
wanghqc
authored
39eab74
graph : fix unused input tensors in minimax m3 graph (#26519)
ggerganov
authored
c50b34a
model: M3: Move MSA into a new memory implementation (#26338)

timkhronos
and
ggerganov
authored
67d5978

Back | FazBrowse Home | New Git URL