Johannes Gäßler 7483d2b61c CUDA: use tensor cores for MMQ (llama/7676) ...

* CUDA: int8 tensor cores for MMQ (legacy quants)

* fix out-of-bounds writes

* __builtin_assume -> GGML_CUDA_ASSUME

* fix writeback returning too early

2024-06-16 18:19:48 +03:00

..

template-instances

CUDA: refactor mmq, dmmv, mmvq (llama/7716)

2024-06-16 18:19:48 +03:00

acc.cu

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

acc.cuh

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

arange.cu

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

arange.cuh

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

argsort.cu

ggml : mul_mat_id use the same tensor for all the experts (llama/6387)

2024-04-07 16:15:57 +03:00

argsort.cuh

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

binbcast.cu

ggml : group all experts in a single ggml_mul_mat_id (llama/6505)

2024-05-13 11:02:26 +03:00

binbcast.cuh

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

clamp.cu

Introduction of CUDA Graphs to LLama.cpp (llama/6766)

2024-05-13 11:02:26 +03:00

clamp.cuh

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

common.cuh

CUDA: use tensor cores for MMQ (llama/7676)

2024-06-16 18:19:48 +03:00

concat.cu

cuda : non-cont concat support (llama/7610)

2024-06-16 18:19:48 +03:00

concat.cuh

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

convert.cu

ggml : drop support for QK_K=64 (llama/7473)

2024-06-16 18:19:48 +03:00

convert.cuh

llama : add Command R Plus support (llama/6491)

2024-04-09 20:26:18 +03:00

cpy.cu

Introduction of CUDA Graphs to LLama.cpp (llama/6766)

2024-05-13 11:02:26 +03:00

cpy.cuh

Introduction of CUDA Graphs to LLama.cpp (llama/6766)

2024-05-13 11:02:26 +03:00

dequantize.cuh

llama : add Command R Plus support (llama/6491)

2024-04-09 20:26:18 +03:00

diagmask.cu

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

diagmask.cuh

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

dmmv.cu

CUDA: refactor mmq, dmmv, mmvq (llama/7716)

2024-06-16 18:19:48 +03:00

dmmv.cuh

sync : llama.cpp (skip)

2024-04-07 16:15:57 +03:00

fattn-common.cuh

CUDA: use tensor cores for MMQ (llama/7676)

2024-06-16 18:19:48 +03:00

fattn-tile-f16.cu

CUDA: use tensor cores for MMQ (llama/7676)

2024-06-16 18:19:48 +03:00

fattn-tile-f16.cuh

CUDA: faster large batch FA without tensor cores (llama/7314)

2024-06-16 18:19:48 +03:00

fattn-tile-f32.cu

CUDA: fix Pascal FA, deq. KV to FP16 for batch > 8 (llama/7681)

2024-06-16 18:19:48 +03:00

fattn-tile-f32.cuh

CUDA: faster large batch FA without tensor cores (llama/7314)

2024-06-16 18:19:48 +03:00

fattn-vec-f16.cu

CUDA: add FP32 FlashAttention vector kernel (llama/7188)

2024-05-14 19:16:29 +03:00

fattn-vec-f16.cuh

CUDA: use tensor cores for MMQ (llama/7676)

2024-06-16 18:19:48 +03:00

fattn-vec-f32.cu

CUDA: add FP32 FlashAttention vector kernel (llama/7188)

2024-05-14 19:16:29 +03:00

fattn-vec-f32.cuh

Fix FlashAttention debug test, FP32 assert (llama/7684)

2024-06-16 18:19:48 +03:00

fattn-wmma-f16.cuh

CUDA: use tensor cores for MMQ (llama/7676)

2024-06-16 18:19:48 +03:00

fattn.cu

CUDA: fix Pascal FA, deq. KV to FP16 for batch > 8 (llama/7681)

2024-06-16 18:19:48 +03:00

fattn.cuh

ggml : add Flash Attention (llama/5021)

2024-05-13 11:02:26 +03:00

getrows.cu

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

getrows.cuh

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

im2col.cu

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

im2col.cuh

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

mma.cuh

CUDA: use tensor cores for MMQ (llama/7676)

2024-06-16 18:19:48 +03:00

mmq.cu

CUDA: revise q8_1 data layout for mul_mat_q (llama/7824)

2024-06-16 18:19:48 +03:00

mmq.cuh

CUDA: use tensor cores for MMQ (llama/7676)

2024-06-16 18:19:48 +03:00

mmvq.cu

CUDA: refactor mmq, dmmv, mmvq (llama/7716)

2024-06-16 18:19:48 +03:00

mmvq.cuh

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

norm.cu

ggml : fix YARN + add tests + add asserts (llama/7617)

2024-06-16 18:19:48 +03:00

norm.cuh

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

pad.cu

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

pad.cuh

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

pool2d.cu

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

pool2d.cuh

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

quantize.cu

CUDA: revise q8_1 data layout for mul_mat_q (llama/7824)

2024-06-16 18:19:48 +03:00

quantize.cuh

CUDA: revise q8_1 data layout for mul_mat_q (llama/7824)

2024-06-16 18:19:48 +03:00

rope.cu

ggml : refactor rope norm/neox (llama/7634)

2024-06-16 18:19:48 +03:00

rope.cuh

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

scale.cu

Introduction of CUDA Graphs to LLama.cpp (llama/6766)

2024-05-13 11:02:26 +03:00

scale.cuh

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

softmax.cu

CUDA: deduplicate FlashAttention code (llama/7352)

2024-06-16 18:19:48 +03:00

softmax.cuh

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

sumrows.cu

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

sumrows.cuh

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

tsembd.cu

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

tsembd.cuh

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

unary.cu

feat: implemented sigmoid function (ggml/806)

2024-05-13 11:02:26 +03:00

unary.cuh

feat: implemented sigmoid function (ggml/806)

2024-05-13 11:02:26 +03:00

upscale.cu

ggml : add ggml_upscale_ext (ggml/814)

2024-06-16 18:19:48 +03:00

upscale.cuh

sync : ggml (#2001)

2024-03-27 18:55:10 +02:00

vecdotq.cuh

CUDA: refactor mmq, dmmv, mmvq (llama/7716)

2024-06-16 18:19:48 +03:00