furyhawk/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-21 02:05:51 +00:00
Code Issues Packages Projects Releases Wiki Activity
10,075 Commits 618 Branches 6,870 Tags
master
Commit Graph
9 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Anav PrasadandGitHub 79bba02a67 CUDA: Support CUDA Virtual Devices (#25228) 
* support cuda virtual devices

* disable NCCL path when virtual devices are used

* label virtual devices in description; add GPUx2 server CI jobs

* code refactor
 2026-07-16 13:37:35 +03:00
Anav PrasadandGitHub 1fd5f48037 clean up unused variables warnings (#23975) 2026-06-02 10:38:37 +08:00
Anav PrasadandGitHub 098705a29e CUDA: fuse SSM_CONV + ADD(bias) + SILU (#22478) 2026-04-30 02:39:56 +08:00
Anav PrasadandGitHub 86db42e97f CUDA: fuse relu + sqr (#22249) 2026-04-23 10:28:56 +08:00
Anav PrasadandGitHub 03b3d07798 Convert: Fix NemotronH Config Parsing (#21664) 
* fix NemotronH vocab loading by using trust_remote_code for unsupported config patterns

* fix NemotronH tokenizer loading by overriding set_vocab with trust_remote_code
 2026-04-16 13:11:45 +03:00
Anav PrasadGitHubJohannes Gäßler
 		88458164c7 CUDA: Add Flash Attention Support for Head Dimension 512 (#20998) 
* flash attention support for head dimension 512 added

* FA D=512 - match 576 configs, limit ncols2, revert vec cap

* fix HIP tile kernel build for D=512

* fix HIP tile kernel occupancy for D=512 on AMD

* Apply suggestions from code review

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* fix tile FA compilation

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
 2026-04-01 09:07:24 +02:00
Anav PrasadandGitHub 01d8eaa28d mtmd : Add Nemotron Nano 12B v2 VL support (#19547) 
* nemotron nano v2 vlm support added

* simplified code; addressed reviews

* pre-downsample position embeddings during GGUF conversion for fixed input size
 2026-02-14 14:07:00 +01:00
Anav PrasadandGitHub 5b6913c47b cuda : remove legacy copy-op pointer indirection code (#16485) 
* remove legacy copy-op pointer indirection code

* further removal of copy-op indirection code

* renamed check_node_graph_compatibility_and_refresh_copy_ops function
 2025-10-14 11:53:49 +02:00
anavp-nvidiaandGitHub a014310374 cuda : Enable CUDA Graph usage for Nemotron Nano v2 (NemotronH) (#16328) 
* Fix Nemotron Nano v2 9B not executing as CUDA Graph on NVIDIA GPUs

* fix to ensure test-backend-ops check passes
 2025-09-30 11:13:22 +03:00