Skip to content

Actions: microsoft/onnxruntime-genai

Actions

Windows CUDA x64 Build

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
win-cuda-x64-build.yml
2,357 workflow runs
2,357 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Allow some known extra inputs in the model Windows CUDA x64 Build #2391: Pull request #1167 synchronize by baijumeswani
January 7, 2025 22:51 18m 37s baijumeswani/num-logits-to-keep
baijumeswani/num-logits-to-keep
January 7, 2025 22:51 18m 37s
Recompute KV cache for Phi3 when switching from short to long factor Windows CUDA x64 Build #2390: Pull request #1161 synchronize by ajindal1
January 7, 2025 21:21 18m 35s abjindal/phi3_reset_compute_cache
abjindal/phi3_reset_compute_cache
January 7, 2025 21:21 18m 35s
Release 0.6.0 Windows CUDA x64 Build #2389: Commit cc6d94e pushed by baijumeswani
January 7, 2025 21:11 22m 6s rel-0.6.0
rel-0.6.0
January 7, 2025 21:11 22m 6s
Allow some known extra inputs in the model Windows CUDA x64 Build #2388: Pull request #1167 synchronize by baijumeswani
January 7, 2025 20:54 19m 12s baijumeswani/num-logits-to-keep
baijumeswani/num-logits-to-keep
January 7, 2025 20:54 19m 12s
Allow some known extra inputs in the model Windows CUDA x64 Build #2387: Pull request #1167 synchronize by baijumeswani
January 7, 2025 19:06 19m 52s baijumeswani/num-logits-to-keep
baijumeswani/num-logits-to-keep
January 7, 2025 19:06 19m 52s
Allow some known extra inputs in the model Windows CUDA x64 Build #2386: Pull request #1167 opened by baijumeswani
January 7, 2025 18:30 19m 31s baijumeswani/num-logits-to-keep
baijumeswani/num-logits-to-keep
January 7, 2025 18:30 19m 31s
Recompute KV cache for Phi3 when switching from short to long factor Windows CUDA x64 Build #2385: Pull request #1161 synchronize by ajindal1
January 6, 2025 23:15 25m 15s abjindal/phi3_reset_compute_cache
abjindal/phi3_reset_compute_cache
January 6, 2025 23:15 25m 15s
Update onnxruntime-extension (#1160) Windows CUDA x64 Build #2384: Commit a715113 pushed by baijumeswani
January 6, 2025 18:17 26m 39s main
main
January 6, 2025 18:17 26m 39s
Fix model path in Phi-3 QA example (#1165) Windows CUDA x64 Build #2383: Commit 7b88a47 pushed by baijumeswani
January 6, 2025 18:14 19m 27s main
main
January 6, 2025 18:14 19m 27s
Address a DML regression caused by the continuous decoding changes Windows CUDA x64 Build #2382: Pull request #1159 synchronize by baijumeswani
January 6, 2025 18:08 22m 35s baijumeswani/fix-dml
baijumeswani/fix-dml
January 6, 2025 18:08 22m 35s
Fix model path in Phi-3 QA example Windows CUDA x64 Build #2381: Pull request #1165 synchronize by kunal-vaishnavi
January 5, 2025 06:08 21m 15s kvaishnavi/phi3-qa
kvaishnavi/phi3-qa
January 5, 2025 06:08 21m 15s
Fix model path in Phi-3 QA example Windows CUDA x64 Build #2380: Pull request #1165 synchronize by kunal-vaishnavi
January 5, 2025 06:07 1m 0s kvaishnavi/phi3-qa
kvaishnavi/phi3-qa
January 5, 2025 06:07 1m 0s
Recompute KV cache for Phi3 when switching from short to long factor Windows CUDA x64 Build #2379: Pull request #1161 synchronize by ajindal1
January 3, 2025 01:04 22m 35s abjindal/phi3_reset_compute_cache
abjindal/phi3_reset_compute_cache
January 3, 2025 01:04 22m 35s
Fix model path in Phi-3 QA example Windows CUDA x64 Build #2378: Pull request #1165 opened by kunal-vaishnavi
January 2, 2025 22:10 26m 21s kvaishnavi/phi3-qa
kvaishnavi/phi3-qa
January 2, 2025 22:10 26m 21s
Update onnxruntime-extension Windows CUDA x64 Build #2377: Pull request #1160 synchronize by skyline75489
December 25, 2024 06:42 28m 18s jialli/ortx
jialli/ortx
December 25, 2024 06:42 28m 18s
Update onnxruntime-extension Windows CUDA x64 Build #2376: Pull request #1160 synchronize by skyline75489
December 23, 2024 06:45 22m 16s jialli/ortx
jialli/ortx
December 23, 2024 06:45 22m 16s
Update onnxruntime-extension Windows CUDA x64 Build #2375: Pull request #1160 synchronize by skyline75489
December 23, 2024 06:43 2m 7s jialli/ortx
jialli/ortx
December 23, 2024 06:43 2m 7s
[Model builder] Add option to exclude cache in inputs and outputs Windows CUDA x64 Build #2374: Pull request #1162 opened by xenova
December 22, 2024 12:09 26m 12s xenova:patch-1
xenova:patch-1
December 22, 2024 12:09 26m 12s
Add Granite to model builder Windows CUDA x64 Build #2373: Pull request #1153 synchronize by kunal-vaishnavi
December 21, 2024 00:25 33m 6s kvaishnavi/granite
kvaishnavi/granite
December 21, 2024 00:25 33m 6s
Recompute KV cache for Phi3 when switching from short to long factor Windows CUDA x64 Build #2372: Pull request #1161 synchronize by ajindal1
December 20, 2024 23:04 27m 26s abjindal/phi3_reset_compute_cache
abjindal/phi3_reset_compute_cache
December 20, 2024 23:04 27m 26s
Update ORT GenAI examples (#1150) Windows CUDA x64 Build #2371: Commit daefc4f pushed by kunal-vaishnavi
December 20, 2024 21:03 22m 39s main
main
December 20, 2024 21:03 22m 39s
Address a DML regression caused by the continuous decoding changes Windows CUDA x64 Build #2370: Pull request #1159 synchronize by baijumeswani
December 20, 2024 20:29 23m 25s baijumeswani/fix-dml
baijumeswani/fix-dml
December 20, 2024 20:29 23m 25s
Recompute KV cache for Phi3 when switching from short to long factor Windows CUDA x64 Build #2369: Pull request #1161 synchronize by ajindal1
December 20, 2024 19:37 19m 39s abjindal/phi3_reset_compute_cache
abjindal/phi3_reset_compute_cache
December 20, 2024 19:37 19m 39s
Recompute KV cache for Phi3 when switching from short to long factor Windows CUDA x64 Build #2368: Pull request #1161 opened by ajindal1
December 20, 2024 19:20 9m 29s abjindal/phi3_reset_compute_cache
abjindal/phi3_reset_compute_cache
December 20, 2024 19:20 9m 29s
Add pre-generated prompts option for benchmark Windows CUDA x64 Build #2367: Pull request #1091 synchronize by omer-demir
December 20, 2024 19:00 24m 35s omer-demir:omerdemir/pre_generated_prompts
omer-demir:omerdemir/pre_generated_prompts
December 20, 2024 19:00 24m 35s