Skip to content

Actions: nod-ai/shark-ai

CI - shortfin - Python 3.13 Free-threaded

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
761 workflow runs
761 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Refactor llama / mixtral / grok for shared features
CI - shortfin - Python 3.13 Free-threaded #219: Pull request #267 synchronize by rsuderman
October 16, 2024 00:02 3m 57s rsuderman:refactor_llm
October 16, 2024 00:02 3m 57s
[tuner] Update gpu pipeline option handling
CI - shortfin - Python 3.13 Free-threaded #218: Pull request #282 opened by kuhar
October 15, 2024 21:25 4m 19s kuhar:pipeline-options
October 15, 2024 21:25 4m 19s
[sharktank] Evaluation - Add Perplexity test
CI - shortfin - Python 3.13 Free-threaded #217: Pull request #233 synchronize by archana-ramalingam
October 15, 2024 19:37 4m 26s perplexity-test
October 15, 2024 19:37 4m 26s
[libshortfin] Bump nanobind to version 2.0.0 (#278)
CI - shortfin - Python 3.13 Free-threaded #216: Commit f8fd09b pushed by marbre
October 15, 2024 17:23 4m 35s main
October 15, 2024 17:23 4m 35s
[libshortfin] Bump nanobind to version 2.0.0
CI - shortfin - Python 3.13 Free-threaded #215: Pull request #278 synchronize by marbre
October 15, 2024 17:21 4m 57s marbre:nanobind
October 15, 2024 17:21 4m 57s
Refresh metadata in sharktank/setup.py.
CI - shortfin - Python 3.13 Free-threaded #214: Pull request #247 synchronize by ScottTodd
October 15, 2024 16:44 5m 10s ScottTodd:sharktank-package-metadata
October 15, 2024 16:44 5m 10s
Put in some docs about how parameters are loaded
CI - shortfin - Python 3.13 Free-threaded #213: Pull request #281 opened by renxida
October 15, 2024 15:09 5m 9s renxida:document-shortfin-parameter-loading
October 15, 2024 15:09 5m 9s
Add device selection to shortfin llm demo
CI - shortfin - Python 3.13 Free-threaded #212: Pull request #275 synchronize by renxida
October 15, 2024 15:06 4m 31s renxida:shortfin-system-selection
October 15, 2024 15:06 4m 31s
Add device selection to shortfin llm demo
CI - shortfin - Python 3.13 Free-threaded #211: Pull request #275 synchronize by renxida
October 15, 2024 14:22 4m 38s renxida:shortfin-system-selection
October 15, 2024 14:22 4m 38s
[llama] Update kv cache to have read/write functions
CI - shortfin - Python 3.13 Free-threaded #210: Pull request #280 synchronize by rsuderman
October 15, 2024 05:41 4m 21s rsuderman:kv_cache_refactor
October 15, 2024 05:41 4m 21s
[llama] Update kv cache to have read/write functions
CI - shortfin - Python 3.13 Free-threaded #209: Pull request #280 synchronize by rsuderman
October 15, 2024 05:27 4m 57s rsuderman:kv_cache_refactor
October 15, 2024 05:27 4m 57s
[llama] Update kv cache to have read/write functions
CI - shortfin - Python 3.13 Free-threaded #208: Pull request #280 synchronize by rsuderman
October 15, 2024 04:18 5m 3s rsuderman:kv_cache_refactor
October 15, 2024 04:18 5m 3s
[llama] Update kv cache to have read/write functions
CI - shortfin - Python 3.13 Free-threaded #207: Pull request #280 synchronize by rsuderman
October 15, 2024 04:14 4m 30s rsuderman:kv_cache_refactor
October 15, 2024 04:14 4m 30s
[llama] Update kv cache to have read/write functions
CI - shortfin - Python 3.13 Free-threaded #206: Pull request #280 opened by rsuderman
October 15, 2024 02:04 4m 51s rsuderman:kv_cache_refactor
October 15, 2024 02:04 4m 51s
Add device selection to shortfin llm demo
CI - shortfin - Python 3.13 Free-threaded #205: Pull request #275 synchronize by renxida
October 15, 2024 00:47 5m 58s renxida:shortfin-system-selection
October 15, 2024 00:47 5m 58s
Add fp8 quantization for conv and linear layers
CI - shortfin - Python 3.13 Free-threaded #204: Pull request #277 synchronize by nithinsubbiah
October 15, 2024 00:08 3m 55s nithinsubbiah:punet_f8
October 15, 2024 00:08 3m 55s
Add fp8 quantization for conv and linear layers
CI - shortfin - Python 3.13 Free-threaded #203: Pull request #277 synchronize by nithinsubbiah
October 15, 2024 00:03 4m 6s nithinsubbiah:punet_f8
October 15, 2024 00:03 4m 6s
Add fp8 quantization for conv and linear layers
CI - shortfin - Python 3.13 Free-threaded #202: Pull request #277 synchronize by nithinsubbiah
October 14, 2024 23:55 4m 34s nithinsubbiah:punet_f8
October 14, 2024 23:55 4m 34s
Add fp8 quantization for conv and linear layers
CI - shortfin - Python 3.13 Free-threaded #201: Pull request #277 synchronize by nithinsubbiah
October 14, 2024 23:53 2m 53s nithinsubbiah:punet_f8
October 14, 2024 23:53 2m 53s
Fix the default case of the einsum operation override
CI - shortfin - Python 3.13 Free-threaded #200: Pull request #279 opened by KyleHerndon
October 14, 2024 21:38 4m 0s einsum_fix
October 14, 2024 21:38 4m 0s
Refactor llama / mixtral / grok for shared features
CI - shortfin - Python 3.13 Free-threaded #199: Pull request #267 synchronize by rsuderman
October 14, 2024 20:20 4m 21s rsuderman:refactor_llm
October 14, 2024 20:20 4m 21s
Rework RotaryEmbedding for dynamic computation
CI - shortfin - Python 3.13 Free-threaded #198: Pull request #255 synchronize by rsuderman
October 14, 2024 20:02 3m 55s rsuderman:rework_rotary
October 14, 2024 20:02 3m 55s
Add special einsum cases that lower to batch matmul
CI - shortfin - Python 3.13 Free-threaded #197: Pull request #262 synchronize by KyleHerndon
October 14, 2024 19:53 3m 52s einsum_matmul
October 14, 2024 19:53 3m 52s
Add sharded paged attention test
CI - shortfin - Python 3.13 Free-threaded #196: Pull request #276 synchronize by sogartar
October 14, 2024 19:19 4m 22s sogartar:sharded-paged-attention-test
October 14, 2024 19:19 4m 22s
Add sharded paged attention test
CI - shortfin - Python 3.13 Free-threaded #195: Pull request #276 synchronize by sogartar
October 14, 2024 19:13 4m 24s sogartar:sharded-paged-attention-test
October 14, 2024 19:13 4m 24s
ProTip! You can narrow down the results and go further in time using created:<2024-10-14 or the other filters available.