Skip to content

Actions: b4rtaz/distributed-llama

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
322 workflow runs
322 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

feat: add llama3_1_405b_instruct_q40 to launch.py. (#112)
main #288: Commit 5244daa pushed by b4rtaz
July 31, 2024 14:22 8m 25s main
July 31, 2024 14:22 8m 25s
feat: dev mode.
main #286: Commit ee2c689 pushed by b4rtaz
July 31, 2024 08:57 11m 5s main
July 31, 2024 08:57 11m 5s
feat: improved performance of quantization to q40. (#111)
main #285: Commit f18ac63 pushed by b4rtaz
July 30, 2024 19:28 6m 11s main
July 30, 2024 19:28 6m 11s
feat: improved performance of quantization to q40.
main #284: Pull request #111 opened by b4rtaz
July 30, 2024 19:28 5m 33s feat/q40-speed-up
July 30, 2024 19:28 5m 33s
feat: --max-seq-len argument. (#109)
main #283: Commit 71135e6 pushed by b4rtaz
July 29, 2024 12:22 6m 6s main
July 29, 2024 12:22 6m 6s
feat: --max-seq-len argument.
main #282: Pull request #109 opened by b4rtaz
July 29, 2024 12:14 6m 47s feat/max-seq-len
July 29, 2024 12:14 6m 47s
convert-hf.py, skipping hidden files.
main #281: Commit 57e3807 pushed by b4rtaz
July 28, 2024 19:51 6m 49s main
July 28, 2024 19:51 6m 49s
update readme.md.
main #280: Commit 2339746 pushed by b4rtaz
July 28, 2024 14:25 6m 16s main
July 28, 2024 14:25 6m 16s
feat: fallback implementation for matmulQ40vQ80.
main #279: Commit 755cdf2 pushed by b4rtaz
July 28, 2024 14:12 6m 13s main
July 28, 2024 14:12 6m 13s
fix: set bufferSize.
main #278: Commit 9a729c9 pushed by b4rtaz
July 27, 2024 09:14 5m 34s main
July 27, 2024 09:14 5m 34s
update readme.md.
main #277: Commit dc0e94f pushed by b4rtaz
July 25, 2024 19:49 9m 37s main
July 25, 2024 19:49 9m 37s
feat: support llama 3.1. (#106)
main #276: Commit 4b8a0ca pushed by b4rtaz
July 25, 2024 11:53 6m 40s main
July 25, 2024 11:53 6m 40s
feat: support llama 3.1.
main #275: Pull request #106 synchronize by b4rtaz
July 25, 2024 11:46 5m 38s feat/llama-3.1
July 25, 2024 11:46 5m 38s
feat: support llama 3.1.
main #274: Pull request #106 synchronize by b4rtaz
July 25, 2024 10:41 6m 9s feat/llama-3.1
July 25, 2024 10:41 6m 9s
feat: support llama 3.1.
main #273: Pull request #106 synchronize by b4rtaz
July 25, 2024 09:59 5m 58s feat/llama-3.1
July 25, 2024 09:59 5m 58s
feat: support llama 3.1.
main #272: Pull request #106 synchronize by b4rtaz
July 25, 2024 07:01 6m 17s feat/llama-3.1
July 25, 2024 07:01 6m 17s
feat: support llama 3.1.
main #271: Pull request #106 synchronize by b4rtaz
July 25, 2024 06:57 1m 49s feat/llama-3.1
July 25, 2024 06:57 1m 49s
feat: support llama 3.1.
main #270: Pull request #106 synchronize by b4rtaz
July 25, 2024 06:54 1m 44s feat/llama-3.1
July 25, 2024 06:54 1m 44s
feat: support llama 3.1.
main #269: Pull request #106 opened by b4rtaz
July 24, 2024 22:53 1m 39s feat/llama-3.1
July 24, 2024 22:53 1m 39s
revert: old report.pdf.
main #268: Commit 8c57298 pushed by b4rtaz
July 24, 2024 10:51 5m 48s main
July 24, 2024 10:51 5m 48s
fix: url to llama2 tokenizer.
main #267: Commit 1880cf3 pushed by b4rtaz
July 19, 2024 07:41 6m 29s main
July 19, 2024 07:41 6m 29s
feat: chat-template argument. (#100)
main #266: Commit 90d7ebd pushed by b4rtaz
July 12, 2024 20:09 5m 35s main
July 12, 2024 20:09 5m 35s
feat: chat-template argument.
main #265: Pull request #100 synchronize by b4rtaz
July 12, 2024 19:56 6m 30s feat/chat-template-argument
July 12, 2024 19:56 6m 30s
feat: chat-template argument.
main #264: Pull request #100 opened by b4rtaz
July 12, 2024 19:55 2m 20s feat/chat-template-argument
July 12, 2024 19:55 2m 20s