Skip to content

Actions: nod-ai/shark-ai

Llama Benchmarking 8B Tests

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
2,699 workflow runs
2,699 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Initial pipeline parallelism support
Llama Benchmarking 8B Tests #2675: Pull request #1008 synchronize by Alex-Vasile
March 4, 2025 16:03 4m 25s Alex-Vasile:pipeline
March 4, 2025 16:03 4m 25s
Install PyTorch for ROCM instead of CPU-only
Llama Benchmarking 8B Tests #2671: Pull request #1032 synchronize by marbre
March 4, 2025 07:59 8m 16s marbre:pytorch-rocm
March 4, 2025 07:59 8m 16s
Install PyTorch for ROCM instead of CPU-only
Llama Benchmarking 8B Tests #2670: Pull request #1032 opened by marbre
March 4, 2025 07:58 1m 6s marbre:pytorch-rocm
March 4, 2025 07:58 1m 6s
Fix llama fp8 benchmark test and remove decomposed benchmarking tests
Llama Benchmarking 8B Tests #2669: Pull request #1000 synchronize by aviator19941
March 4, 2025 06:29 2m 53s fix_llama_fp8_benchmark_test
March 4, 2025 06:29 2m 53s
Fix llama fp8 benchmark test and remove decomposed benchmarking tests
Llama Benchmarking 8B Tests #2668: Pull request #1000 synchronize by aviator19941
March 4, 2025 04:34 24m 56s fix_llama_fp8_benchmark_test
March 4, 2025 04:34 24m 56s
[Shortfin][SD] Error out on invalid ports (#1029)
Llama Benchmarking 8B Tests #2666: Commit 4bd757a pushed by kuhar
March 4, 2025 03:04 6m 5s main
March 4, 2025 03:04 6m 5s
[Shortfin][SD] Error out on invalid ports
Llama Benchmarking 8B Tests #2663: Pull request #1029 opened by kuhar
March 4, 2025 01:11 5m 21s kuhar:port-error
March 4, 2025 01:11 5m 21s
Make kv_cache read operation perform a single gather
Llama Benchmarking 8B Tests #2661: Pull request #1027 synchronize by rsuderman
March 4, 2025 00:57 4m 51s rsuderman:kv_single_gather
March 4, 2025 00:57 4m 51s
Make kv_cache read operation perform a single gather
Llama Benchmarking 8B Tests #2660: Pull request #1027 opened by rsuderman
March 4, 2025 00:56 44s rsuderman:kv_single_gather
March 4, 2025 00:56 44s
Fix llama fp8 benchmark test and remove decomposed benchmarking tests
Llama Benchmarking 8B Tests #2659: Pull request #1000 synchronize by aviator19941
March 4, 2025 00:19 3m 15s fix_llama_fp8_benchmark_test
March 4, 2025 00:19 3m 15s
Refactoring more GenerateService functions across shortfin apps
Llama Benchmarking 8B Tests #2658: Pull request #1010 synchronize by KyleHerndon
March 4, 2025 00:01 4m 49s shortfin-refactor-2
March 4, 2025 00:01 4m 49s
Remove topology usage from sdxl readme. (#1026)
Llama Benchmarking 8B Tests #2657: Commit 29a1ee7 pushed by monorimet
March 3, 2025 23:45 7m 7s main
March 3, 2025 23:45 7m 7s
Rewriter write_timestep to fuse the indexing writes (#1023)
Llama Benchmarking 8B Tests #2656: Commit 7bddd07 pushed by rsuderman
March 3, 2025 23:45 5m 29s main
March 3, 2025 23:45 5m 29s
Remove topology usage from sdxl readme.
Llama Benchmarking 8B Tests #2655: Pull request #1026 opened by monorimet
March 3, 2025 23:15 4m 51s monorimet-patch-1
March 3, 2025 23:15 4m 51s