Shupei Fan
|
c202cef168
ggml-cpu: support IQ4_NL_4_4 by runtime repack (#10541)
|
1 ano atrás |
Diego Devesa
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 ano atrás |
Johannes Gäßler
|
8a43e940ab
ggml: new optimization interface (ggml/988)
|
1 ano atrás |
Diego Devesa
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 ano atrás |
Georgi Gerganov
|
841f27abdb
metal : optimize FA kernels (#10171)
|
1 ano atrás |
Zhiyuan Li
|
3bcd40b3c5
Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133)
|
1 ano atrás |
Diego Devesa
|
9f40989351
ggml : move CPU backend to a separate file (#10144)
|
1 ano atrás |
Diego Devesa
|
a6744e43e8
llama : add simple-chat example (#10124)
|
1 ano atrás |
Georgi Gerganov
|
1804adb0cf
ggml : remove ggml_scratch (#10121)
|
1 ano atrás |
Georgi Gerganov
|
f221d56220
ggml : alloc ggml_contexts on the heap (whisper/2525)
|
1 ano atrás |
Ma Mingfei
|
60ce97c9d8
add amx kernel for gemm (#8998)
|
1 ano atrás |
Diego Devesa
|
dca1d4b58a
ggml : fix BLAS with unsupported types (#9775)
|
1 ano atrás |
Johannes Gäßler
|
fabdc3bda3
ggml/ex: calculate accuracy in graph, adapt MNIST (ggml/980)
|
1 ano atrás |
bandoti
|
d6fe7abf04
ggml: unify backend logging mechanism (#9709)
|
1 ano atrás |
Diego Devesa
|
c83ad6d01e
ggml-backend : add device and backend reg interfaces (#9707)
|
1 ano atrás |
Johannes Gäßler
|
e98c1c188e
test: fix OPT_STEP_ADAMW for test-backend-ops (ggml/974)
|
1 ano atrás |
Johannes Gäßler
|
7254cdf7e8
ggml: fix gradient allocation logic (ggml/966)
|
1 ano atrás |
Georgi Gerganov
|
6084bfb261
ggml : fix GGML_MAX_N_THREADS + improve formatting (ggml/969)
|
1 ano atrás |
Dan Johansson
|
6a0f779484
ggml : add run-time detection of neon, i8mm and sve (#9331)
|
1 ano atrás |
Georgi Gerganov
|
c038931615
examples : adapt to ggml.h changes (ggml/0)
|
1 ano atrás |
Georgi Gerganov
|
cea1486ecf
log : add CONT level for continuing previous log entry (#9610)
|
1 ano atrás |
Johannes Gäßler
|
424c5d00a9
ggml/examples: add backend support for numerical optimization (ggml/949)
|
1 ano atrás |
Georgi Gerganov
|
6262d13e0b
common : reimplement logging (#9418)
|
1 ano atrás |
Ahmad Tameem
|
2b00fa7997
riscv : modify Makefile and add a RISCV_VECT to print log info (#9442)
|
1 ano atrás |
Georgi Gerganov
|
d6a04f872d
ggml : hide ggml_object, ggml_cgraph, ggml_hash_set (#9408)
|
1 ano atrás |
Johannes Gäßler
|
202084d31d
tests: add gradient tests for all backends (ggml/932)
|
1 ano atrás |
Johannes Gäßler
|
dbbebcab33
ggml: fix ggml_graph_cpy undefined behavior (ggml/943)
|
1 ano atrás |
compilade
|
9bc6db28d0
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)
|
1 ano atrás |
Molly Sophia
|
8f1d81a0b6
llama : support RWKV v6 models (#8980)
|
1 ano atrás |
Faisal Zaghloul
|
42c76d1358
Threadpool: take 2 (#8672)
|
1 ano atrás |