Skip to content

Actions: hipudding/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
179 workflow runs
179 workflow runs

Filter by Workflow

⌥ + click/return to exclude

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
cann: add SWIGLU_OAI and ADD_ID op support for gpt-oss MoE .github/workflows/build-cann.yml #4: Commit 182655e pushed by hipudding
Failure FA
FA
Failure
cann: upgrade flash attention from V2 to V5 for sinks and asymmetric … .github/workflows/build-cann.yml #3: Commit 886c3a2 pushed by hipudding
Failure FA
FA
Failure
cann: upgrade flash attention from V2 to V5 for sinks and asymmetric … .github/workflows/build-cann.yml #2: Commit 4c194fb pushed by hipudding
Failure FA
FA
Failure
cann: upgrade flash attention from V2 to V5 for sinks and asymmetric … Check Pre-Tokenizer Hashes #27: Commit 09b2345 pushed by hipudding
1d 0h 0m 1s FA
FA
1d 0h 0m 1s
cann: upgrade flash attention from V2 to V5 for sinks and asymmetric … Update Operations Documentation #22: Commit 09b2345 pushed by hipudding
1d 0h 0m 1s FA
FA
1d 0h 0m 1s
cann: upgrade flash attention from V2 to V5 for sinks and asymmetric … Python Type-Check #42: Commit 09b2345 pushed by hipudding
1d 0h 0m 2s FA
FA
1d 0h 0m 2s
cann: upgrade flash attention from V2 to V5 for sinks and asymmetric … Python check requirements.txt #45: Commit 09b2345 pushed by hipudding
1d 0h 0m 2s FA
FA
1d 0h 0m 2s
cann: upgrade flash attention from V2 to V5 for sinks and asymmetric … .github/workflows/build-cann.yml #1: Commit 09b2345 pushed by hipudding
Failure FA
FA
Failure
CANN: add new ops, optimize existing ops Check Pre-Tokenizer Hashes #26: Commit 01f5ebd pushed by hipudding
58s qwen35_op
qwen35_op
58s
CANN: add new ops, optimize existing ops Python Type-Check #41: Commit 01f5ebd pushed by hipudding
2m 24s qwen35_op
qwen35_op
2m 24s
CANN: add new ops, optimize existing ops Python check requirements.txt #44: Commit 01f5ebd pushed by hipudding
5m 2s qwen35_op
qwen35_op
5m 2s
Merge branch 'master' into qwen35_op Update Operations Documentation #21: Commit a51b6d0 pushed by hipudding
28s qwen35_op
qwen35_op
28s
Merge branch 'master' into qwen35_op Python check requirements.txt #43: Commit a51b6d0 pushed by hipudding
5m 5s qwen35_op
qwen35_op
5m 5s
Merge branch 'master' into qwen35_op Check Pre-Tokenizer Hashes #25: Commit a51b6d0 pushed by hipudding
55s qwen35_op
qwen35_op
55s
Merge branch 'master' into qwen35_op Python Type-Check #40: Commit a51b6d0 pushed by hipudding
2m 43s qwen35_op
qwen35_op
2m 43s
cann: implement backend memset_tensor interface Check Pre-Tokenizer Hashes #24: Commit c9dcafa pushed by hipudding
59s ocp
ocp
59s
cann: implement backend memset_tensor interface Copilot Setup Steps #7: Commit c9dcafa pushed by hipudding
1m 53s ocp
ocp
1m 53s
cann: implement backend memset_tensor interface Python Type-Check #39: Commit c9dcafa pushed by hipudding
3m 29s ocp
ocp
3m 29s
cann: implement backend memset_tensor interface Python check requirements.txt #42: Commit c9dcafa pushed by hipudding
5m 26s ocp
ocp
5m 26s
CANN: fix multi-thread set_tensor race conditions Update Operations Documentation #20: Commit aeee6b4 pushed by hipudding
59s ocp
ocp
59s
CANN: fix multi-thread set_tensor race conditions Python Type-Check #38: Commit aeee6b4 pushed by hipudding
3m 7s ocp
ocp
3m 7s
CANN: fix multi-thread set_tensor race conditions Python check requirements.txt #41: Commit aeee6b4 pushed by hipudding
5m 31s ocp
ocp
5m 31s
CANN: fix multi-thread set_tensor race conditions Check Pre-Tokenizer Hashes #23: Commit aeee6b4 pushed by hipudding
1m 1s ocp
ocp
1m 1s
CANN: fix multi-thread set_tensor race conditions Copilot Setup Steps #6: Commit aeee6b4 pushed by hipudding
1m 59s ocp
ocp
1m 59s
CANN: fix multi-thread set_tensor race conditions Update Operations Documentation #19: Commit b9305e7 pushed by hipudding
41s ocp
ocp
41s