Skip to content

Actions: b4rtaz/distributed-llama

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
318 workflow runs
318 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

API Server
main #134: Pull request #47 synchronize by b4rtaz
May 19, 2024 19:00 19s DifferentialityDevelopment:main
May 19, 2024 19:00 19s
API Server
main #133: Pull request #47 synchronize by b4rtaz
May 19, 2024 16:43 55s DifferentialityDevelopment:main
May 19, 2024 16:43 55s
feat: use avx2 to speedup dotProduct (#57)
main #132: Commit 182fdcd pushed by b4rtaz
May 18, 2024 09:26 57s main
May 18, 2024 09:26 57s
feat: use avx2 to speedup dotProduct
main #131: Pull request #57 synchronize by b4rtaz
May 18, 2024 09:24 56s feat/dotproduct-avx2
May 18, 2024 09:24 56s
feat: use avx2 to speedup dotProduct
main #130: Pull request #57 synchronize by b4rtaz
May 18, 2024 09:16 55s feat/dotproduct-avx2
May 18, 2024 09:16 55s
feat: use avx2 to speedup dotProduct
main #129: Pull request #57 synchronize by b4rtaz
May 18, 2024 09:12 57s feat/dotproduct-avx2
May 18, 2024 09:12 57s
feat: use avx2 to speedup dotProduct
main #128: Pull request #57 synchronize by b4rtaz
May 18, 2024 09:04 1m 7s feat/dotproduct-avx2
May 18, 2024 09:04 1m 7s
feat: use avx2 to speedup dotProduct
main #127: Pull request #57 synchronize by b4rtaz
May 18, 2024 09:04 56s feat/dotproduct-avx2
May 18, 2024 09:04 56s
feat: use avx2 to speedup dotProduct
main #126: Pull request #57 synchronize by b4rtaz
May 18, 2024 08:59 1m 4s feat/dotproduct-avx2
May 18, 2024 08:59 1m 4s
feat: use avx2 to speedup dotProduct
main #125: Pull request #57 opened by b4rtaz
May 18, 2024 08:36 55s feat/dotproduct-avx2
May 18, 2024 08:36 55s
feat: use avx2 to speedup matmulF32 (#56)
main #124: Commit be9929b pushed by b4rtaz
May 18, 2024 07:34 53s main
May 18, 2024 07:34 53s
feat: use avx2 to speedup matmulF32
main #123: Pull request #56 opened by b4rtaz
May 18, 2024 07:33 1m 7s feat/matmul-f32
May 18, 2024 07:33 1m 7s
feat: use avx2 to speedup matmulQ40 (#54)
main #121: Commit d1304c8 pushed by b4rtaz
May 15, 2024 07:49 58s main
May 15, 2024 07:49 58s
fix: alloc mem.
main #114: Commit 0faf794 pushed by b4rtaz
May 14, 2024 07:07 1m 4s main
May 14, 2024 07:07 1m 4s
fix: convert-llama.py supports different max_seq_len. (#51)
main #113: Commit c9bb613 pushed by b4rtaz
May 13, 2024 22:06 56s main
May 13, 2024 22:06 56s
feat: splitting attention layers into all nodes. (#46)
main #111: Commit af8b317 pushed by b4rtaz
May 13, 2024 21:27 59s main
May 13, 2024 21:27 59s
feat: splitting multihead attention into all nodes.
main #110: Pull request #46 synchronize by b4rtaz
May 13, 2024 21:25 55s feat/qkv
May 13, 2024 21:25 55s
feat: splitting multihead attention into all nodes.
main #102: Pull request #46 synchronize by b4rtaz
May 11, 2024 21:02 54s feat/qkv
May 11, 2024 21:02 54s
feat: avg tokens / second. (#44)
main #101: Commit 0f3c9e9 pushed by b4rtaz
May 11, 2024 20:48 56s main
May 11, 2024 20:48 56s
fix.
main #100: Commit dbc8a0d pushed by b4rtaz
May 11, 2024 20:46 1m 2s main
May 11, 2024 20:46 1m 2s
feat: splitting multihead attention into all nodes.
main #99: Pull request #46 synchronize by b4rtaz
May 11, 2024 20:38 55s feat/qkv
May 11, 2024 20:38 55s
feat: splitting multihead attention into all nodes.
main #98: Pull request #46 synchronize by b4rtaz
May 11, 2024 12:55 1m 0s feat/qkv
May 11, 2024 12:55 1m 0s
feat: splitting multihead attention into all nodes.
main #97: Pull request #46 opened by b4rtaz
May 11, 2024 12:14 1m 9s feat/qkv
May 11, 2024 12:14 1m 9s