Skip to content

Actions: agray3/llama.cpp

flake8 Lint

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
36 workflow runs
36 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

speculative : fix out-of-bounds access (#10289)
flake8 Lint #36: Commit 2a82891 pushed by agray3
November 14, 2024 10:31 26s master
November 14, 2024 10:31 26s
fix q4_0_8_8 format for corrupted tokens issue (#10198)
flake8 Lint #35: Commit 2319126 pushed by agray3
November 7, 2024 12:05 25s master
November 7, 2024 12:05 25s
ag_demonstrate_fattn_memory_issue
flake8 Lint #34: Commit 3488adf pushed by agray3
October 24, 2024 07:56 24s ag_demonstrate_fattn_memory_issue
October 24, 2024 07:56 24s
flake.lock: Update
flake8 Lint #33: Commit 873279b pushed by agray3
October 23, 2024 06:11 20m 14s master
October 23, 2024 06:11 20m 14s
ggml: avoid rebuild of GGML graph for each token (#7456)
flake8 Lint #32: Commit 23214c9 pushed by agray3
October 11, 2024 10:24 20s ag_ggml_graph_caching
October 11, 2024 10:24 20s
common : use common_ prefix for common library functions (#9805)
flake8 Lint #31: Commit 7eee341 pushed by agray3
October 11, 2024 08:14 25s master
October 11, 2024 08:14 25s
addressed comment
flake8 Lint #29: Commit d07dc44 pushed by agray3
October 10, 2024 13:05 20s ag_vectorize_dmmv_access_instructions
October 10, 2024 13:05 20s
perplexity : fix integer overflow (#9783)
flake8 Lint #27: Commit e702206 pushed by agray3
October 9, 2024 15:29 23m 8s master
October 9, 2024 15:29 23m 8s
clear before resize
flake8 Lint #26: Commit b51dacc pushed by agray3
September 20, 2024 08:05 22s ag_check_scale_op_params
September 20, 2024 08:05 22s
Avoid using saved CUDA graph if scale changes
flake8 Lint #23: Commit 3fe1f68 pushed by agray3
September 17, 2024 15:47 21s ag_check_scale_op_params
September 17, 2024 15:47 21s
llama : support IBM Granite architecture (#9412)
flake8 Lint #22: Commit 0d2ec43 pushed by agray3
September 17, 2024 06:50 23s master
September 17, 2024 06:50 23s
Abstract into GGML
flake8 Lint #21: Commit 38f4863 pushed by agray3
August 14, 2024 10:03 21s ag_indirect_copy_dest
August 14, 2024 10:03 21s
llama : model-based max number of graph nodes calculation (#8970)
flake8 Lint #19: Commit 0fd93cd pushed by agray3
August 12, 2024 15:52 29s master
August 12, 2024 15:52 29s
scripts : sync cann files (#0)
flake8 Lint #18: Commit afd27f0 pushed by agray3
August 8, 2024 13:20 23s master
August 8, 2024 13:20 23s
make n_embd_v_gqa_* dependent on layer
flake8 Lint #17: Commit d9c7b61 pushed by agray3
July 27, 2024 19:01 20s ag_ggml_graph_caching
July 27, 2024 19:01 20s
remove stale code
flake8 Lint #15: Commit 5289a6a pushed by agray3
July 23, 2024 20:11 23s ag_ggml_graph_caching
July 23, 2024 20:11 23s
restrict to nsplit=2
flake8 Lint #13: Commit a34900a pushed by agray3
July 10, 2024 10:29 18s ag_ggml_graph_caching
July 10, 2024 10:29 18s
fix seg fault
flake8 Lint #12: Commit b7956a8 pushed by agray3
July 8, 2024 15:44 18s ag_ggml_graph_caching
July 8, 2024 15:44 18s