llama.cpp : fix --leave-output-tensor for llama-quantize.#9829

Closed

drollings wants to merge 38 commits intoggml-org:masterfrom

drollings:fix_quantize_leave_output_tensor

Commits on Oct 10, 2024

llama.cpp : fix --leave-output-tensor for llama-quantize.
drollings
committed

Commits on Oct 18, 2024

ggml : move more prints to the ggml log system (#9839)

slaren
authored and
drollings
committed
musa : update doc (#9856)

yeahdongcn
authored and
drollings
committed
llama : improve infill support and special token detection (#9798)

ggerganov
authored and
drollings
committed
server : remove legacy system_prompt feature (#9857)

ggerganov
authored and
drollings
committed
server : remove self-extend features (#9860)

ggerganov
authored and
drollings
committed
server : add option to time limit the generation phase (#9865)

ggerganov
authored and
drollings
committed
flake.lock: Update (#9870)

authored and
drollings
committed
server : reuse cached context chunks (#9866)

ggerganov
authored and
drollings
committed
server : accept extra_context for the infill endpoint (#9874)

ggerganov
authored and
drollings
committed
Vectorize load instructions in dmmv f16 CUDA kernel (#9816)

authored and
drollings
committed
server : handle "logprobs" field with false value (#9871)

authored and
drollings
committed
readme : update bindings list (#9889)

srgtuszy
authored and
drollings
committed
server : update preact (#9895)

ggerganov
authored and
drollings
committed
sampling : add XTC sampler (#9742)

MaggotHATE
authored and
drollings
committed
server : improve infill context reuse (#9894)

ggerganov
authored and
drollings
committed
llama : add infill sampler (#9896)

ggerganov
authored and
drollings
committed
[CANN] Fix cann compilation error (#9891)

leo-pony
authored and
drollings
committed
ggml-alloc : remove buffer_id from leaf_alloc (ggml/987)

danbev
authored and
drollings
committed
sync : ggml

ggerganov
authored and
drollings
committed
server : fix the disappearance of the end of the text (#9867)

z80maniac
authored and
drollings
committed
llama : add tensor name for "result_norm" (#9907)

MollySophia
authored and
drollings
committed
grammar : fix JSON Schema for string regex with top-level alt. (#9903)

jemc
authored and
drollings
committed
llava : fix typo in error message [no ci] (#9884)

danbev
authored and
drollings
committed
llama : suppress conversion from 'size_t' to 'int' (#9046)

danbev
authored and
drollings
committed
fix: use `vm_allocate` to allocate CPU backend buffer on macOS (#9875)

giladgd
authored and
drollings
committed
fix: allocating CPU buffer with size `0` (#9917)

giladgd
authored and
drollings
committed
vulkan : add backend registry / device interfaces (#9721)

slaren
authored and
drollings
committed
readme : update bindings list (#9918)

authored and
drollings
committed
llama : infill sampling handle very long tokens (#9924)

ggerganov
authored and
drollings
committed
llama : change warning to debug log

ggerganov
authored and
drollings
committed
readme : remove --memory-f32 references (#9925)

ggerganov
authored and
drollings
committed
llama : rename batch_all to batch (#8881)

danbev
authored and
drollings
committed
server : add n_indent parameter for line indentation requirement (#9929)

ggerganov
authored and
drollings
committed
add amx kernel for gemm (#8998)

mingfeima
authored and
drollings
committed
[SYCL] Add SYCL Backend registry, device and Event Interfaces (#9705)

OuadiElfarouki
authored and
drollings
committed
rpc : backend refactoring (#9912)

rgerganov
authored and
drollings
committed
Merge branch 'master' into fix_quantize_leave_output_tensor
drollings
committed