Kawrakow d14c479090 Better VRAM utilization strategy for split mode graph (#1126) ...

* Better VRAM utilization strategy for split mode graph

* Fix assert when --max-gpu is less than available GPUs

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

2026-01-09 13:36:02 +02:00

..

CMakeLists.txt

Enable and clean up compiler warnings in src (#824)

2025-10-11 16:01:13 +03:00

llama-arch.cpp

Mimo-V2-Flash support (#1096)

2026-01-05 08:00:01 +02:00

llama-arch.h

Mimo-V2-Flash support (#1096)

2026-01-05 08:00:01 +02:00

llama-build-context.cpp

Split mode "graph" for Ernie-4.5-MoE (#1121)

2026-01-08 16:46:41 +02:00

llama-build-context.h

Split mode 'graph' fpr Qwen3-VL (#1107)

2026-01-05 17:32:00 +02:00

llama-context.h

POC: CUDA tensor parallel (MoE models) (#1022)

2025-12-01 19:25:40 +01:00

llama-cparams.h

Async compute graph evaluation (2 or more GPUs) (#1089)

2025-12-27 08:18:06 +01:00

llama-grammar.cpp

Update grammar (#1023)

2025-11-30 18:45:38 +01:00

llama-grammar.h

Update grammar (#1023)

2025-11-30 18:45:38 +01:00

llama-hparams.cpp

Mimo-V2-Flash support (#1096)

2026-01-05 08:00:01 +02:00

llama-hparams.h

Mimo-V2-Flash support (#1096)

2026-01-05 08:00:01 +02:00

llama-impl.h

POC: CUDA tensor parallel (MoE models) (#1022)

2025-12-01 19:25:40 +01:00

llama-load-tensors.cpp

Better VRAM utilization strategy for split mode graph (#1126)

2026-01-09 13:36:02 +02:00

llama-mmap.cpp

Enable CUDA graphs for MoE models + GPT-OSS support (#689)

2025-08-15 09:18:07 +03:00

llama-mmap.h

Enable CUDA graphs for MoE models + GPT-OSS support (#689)

2025-08-15 09:18:07 +03:00

llama-model-loader.cpp

CUDA: set compute parameters via command line arguments (#910)

2025-11-07 07:11:23 +02:00

llama-model-loader.h

Merge Q, K, V (#878)

2025-10-30 10:49:48 +02:00

llama-model.cpp

Mimo-V2-Flash support (#1096)

2026-01-05 08:00:01 +02:00

llama-model.h

Graph parallel for Mimo-V2-Flash (#1105)

2026-01-05 09:58:54 +02:00

llama-quantize.cpp

Fix requatizing from row-interleaved quants (#992)

2025-11-20 11:50:09 +01:00

llama-sampling.cpp

Update grammar (#1023)

2025-11-30 18:45:38 +01:00

llama-sampling.h

add dry sampler (#513)

2025-06-19 10:24:53 +03:00

llama-vocab.cpp

Update mtmd to improve accuracy of M-RoPE (#993)

2025-11-29 07:27:15 +01:00

llama-vocab.h

Update mtmd to improve accuracy of M-RoPE (#993)

2025-11-29 07:27:15 +01:00

llama.cpp

Split mode "graph" for Ernie-4.5-MoE (#1121)

2026-01-08 16:46:41 +02:00

unicode-data.cpp

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

unicode-data.h

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

unicode.cpp

Enable CUDA graphs for MoE models + GPT-OSS support (#689)

2025-08-15 09:18:07 +03:00

unicode.h

Enable CUDA graphs for MoE models + GPT-OSS support (#689)

2025-08-15 09:18:07 +03:00