Skip to content

Actions: hipudding/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
350 workflow runs
350 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

CANN: fix multi-thread set_tensor race conditions Update Operations Documentation #19: Commit b9305e7 pushed by hipudding
41s ocp
ocp
41s
CANN: fix multi-thread set_tensor race conditions Python Type-Check #37: Commit b9305e7 pushed by hipudding
1m 53s ocp
ocp
1m 53s
CANN: fix multi-thread set_tensor race conditions Python check requirements.txt #40: Commit b9305e7 pushed by hipudding
4m 17s ocp
ocp
4m 17s
CANN: fix multi-thread set_tensor race conditions Check Pre-Tokenizer Hashes #22: Commit b9305e7 pushed by hipudding
59s ocp
ocp
59s
CANN: Support more functions in FA operator Python check requirements.txt #39: Commit 1c219af pushed by hipudding
5m 9s hua
hua
5m 9s
CANN: Support more functions in FA operator Check Pre-Tokenizer Hashes #21: Commit 1c219af pushed by hipudding
59s hua
hua
59s
CANN: Support more functions in FA operator Python Type-Check #36: Commit 1c219af pushed by hipudding
2m 20s hua
hua
2m 20s
CANN: implement quantized MUL_MAT_ID for MoE models Check Pre-Tokenizer Hashes #20: Commit 2d3679b pushed by hipudding
1m 1s mul_mat_id
mul_mat_id
1m 1s
CANN: implement quantized MUL_MAT_ID for MoE models Python check requirements.txt #38: Commit 2d3679b pushed by hipudding
5m 27s mul_mat_id
mul_mat_id
5m 27s
CANN: implement quantized MUL_MAT_ID for MoE models Update Operations Documentation #18: Commit 2d3679b pushed by hipudding
33s mul_mat_id
mul_mat_id
33s
CANN: implement quantized MUL_MAT_ID for MoE models Python Type-Check #35: Commit 2d3679b pushed by hipudding
2m 28s mul_mat_id
mul_mat_id
2m 28s
feat: add multi-stream and operator fusion conflict detection Python Type-Check #34: Commit dd9e377 pushed by hipudding
1m 57s mul_stream
mul_stream
1m 57s
feat: add multi-stream and operator fusion conflict detection Update Operations Documentation #17: Commit dd9e377 pushed by hipudding
36s mul_stream
mul_stream
36s
CANN: implement quantized MUL_MAT_ID for MoE models Python Type-Check #33: Commit 5624c99 pushed by hipudding
2m 20s mul_mat_id
mul_mat_id
2m 20s
ggml-cann: implement quantized MUL_MAT_ID for MoE models Python Type-Check #32: Commit 30bc705 pushed by hipudding
1m 53s mul_mat_id
mul_mat_id
1m 53s
ggml-cann: implement quantized MUL_MAT_ID for MoE models Update Operations Documentation #16: Commit 30bc705 pushed by hipudding
39s mul_mat_id
mul_mat_id
39s
Fix mul_mat_id_quant: use contiguous [M,D] layout for weight tensors Python check requirements.txt #37: Commit e9d05be pushed by hipudding
5m 35s mul_mat_id
mul_mat_id
5m 35s
Fix mul_mat_id_quant: use contiguous [M,D] layout for weight tensors Copilot Setup Steps #5: Commit e9d05be pushed by hipudding
2m 11s mul_mat_id
mul_mat_id
2m 11s
Fix mul_mat_id_quant: use contiguous [M,D] layout for weight tensors Check Pre-Tokenizer Hashes #19: Commit e9d05be pushed by hipudding
57s mul_mat_id
mul_mat_id
57s
Fix mul_mat_id_quant: use contiguous [M,D] layout for weight tensors Update Operations Documentation #15: Commit e9d05be pushed by hipudding
36s mul_mat_id
mul_mat_id
36s
Fix mul_mat_id_quant: use contiguous [M,D] layout for weight tensors Python Type-Check #31: Commit e9d05be pushed by hipudding
2m 21s mul_mat_id
mul_mat_id
2m 21s
docs: update ops.md for CANN backend Update Operations Documentation #14: Commit 0cd2858 pushed by hipudding
12s docs
docs
12s
docs: update ops.md for CANN backend Python check requirements.txt #36: Commit 0cd2858 pushed by hipudding
3m 41s docs
docs
3m 41s
docs: update ops.md for CANN backend Copilot Setup Steps #4: Commit 0cd2858 pushed by hipudding
2m 4s docs
docs
2m 4s
docs: update ops.md for CANN backend Python Type-Check #30: Commit 0cd2858 pushed by hipudding
2m 16s docs
docs
2m 16s