ggml-org/llama.cpp

Pull Requests Commits

ggerganov committed 104 days ago

Verified 81eabb47

ggml : bump version to 0.10.2 (ggml/1474)

ggerganov committed 104 days ago

Verified 7b38b866

ggerganov committed 104 days ago

457e2288

ggml : try fix win32 build (whisper/0)

ggerganov committed 104 days ago

e8ec7ab0

hexagon: hmx flash attention (#22347)

njsyw1997 committed 104 days ago

Verified 1a03cf47

llama-quant : fix `--tensor-type` when default `qtype` is overriden (#22572)

ddh0 committed 104 days ago

Verified b97ebdc9

hexagon: enable non-contiguous row tensor support for unary ops (#22574)

aparmp-quic committed 104 days ago

Verified 2098fd61

webui: Spring Cleaning Refactor v1 (#22505)

allozaur committed 104 days ago

Verified ab6120cd

ggml-webgpu: Fix vectorized handling in mul-mat and mul-mat-id (#22578)

yomaytk committed 105 days ago

Verified c3c15053

vulkan: Support asymmetric FA in coopmat2 path (#21753)

jeffbolznv committed 105 days ago

Verified 05e141a6

ggml-webgpu: add the upscale shader (#22419)

Constannnnnt committed 105 days ago

Verified aab68217

ggml-webgpu: Improve performance of mat-vec and mat-mat for MUL_MAT_ID (#22464)

yomaytk committed 105 days ago

Verified a95a11e5

Update llama-mmap to use ftello/fseeko (#22497)

reeselevine committed 105 days ago

Verified 5cbfb180

common : check for null getpwuid in hf-cache (#22550)

angt committed 105 days ago

Verified beb42fff

vulkan: add get/set tensor 2d functions (#22514)

0cc4m committed 105 days ago

Verified 660b1b4b

spec: fix argument typo (#22552)

barnjamin committed 106 days ago

Verified c20c4451

ci : bump ty to 0.0.33 (#22535)

CISC committed 106 days ago

Verified 6118c043

vendor : update cpp-httplib to 0.43.2 (#22548)

angt committed 106 days ago

Verified 5f0ab726

CUDA: fix tile FA kernel on Pascal (#22541)

JohannesGaessler committed 106 days ago

Verified e82aaf25

scripts : add wc2wt.sh - create worktree from current HEAD (#22513)

ggerganov committed 106 days ago

Verified 27aef3dd

add fast matmul iquants (#22504)

SharmaRithik committed 106 days ago

Verified 45155597

spec : fix draft model checkpoints (#22521)

ggerganov committed 106 days ago

Verified 80afa33a

spec : fix vocab compat checks in spec example (#22426)

petersid2022 committed 106 days ago

Verified b42c7fa5

common : do not pass prompt tokens to reasoning budget sampler (#22488)

aldehir committed 106 days ago

Verified d7759923

hexagon: make vmem and buffer-size configurable (#22487)

max-krasnyansky committed 106 days ago

Verified 41a63be2

CUDA: fuse SSM_CONV + ADD(bias) + SILU (#22478)

anavp-nvidia committed 106 days ago

Verified 098705a2

spec : disacard last drafted token with low prob (#22506)

ggerganov committed 107 days ago

Verified 683c5acb

ggerganov committed 107 days ago

b1d5f5b4

ggml : bump version to 0.10.1 (ggml/1469)

ggerganov committed 107 days ago

4b221b7f

webui: fix slow mic stop and WAV encode (#22480)

ServeurpersoCom committed 107 days ago

Verified 59237bfb

Older