Skip to content

Actions: EricLBuehler/mistral.rs

Actions

Analysis

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
analysis.yaml
1,658 workflow runs
1,658 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Calculate perplexity of ISQ models Analysis #1633: Pull request #931 synchronize by EricLBuehler
November 25, 2024 23:19 59s
November 25, 2024 23:19 59s
Calculate perplexity of ISQ models Analysis #1632: Pull request #931 synchronize by EricLBuehler
November 25, 2024 13:41 1m 6s
November 25, 2024 13:41 1m 6s
Calculate perplexity of ISQ models Analysis #1631: Pull request #931 opened by EricLBuehler
November 25, 2024 02:57 1m 1s
November 25, 2024 02:57 1m 1s
add serde serialization to text chat types Analysis #1630: Pull request #921 synchronize by rozgo
November 25, 2024 00:45 1m 1s
November 25, 2024 00:45 1m 1s
Support fp8 on Metal Analysis #1629: Pull request #930 opened by EricLBuehler
November 24, 2024 10:22 1m 14s
November 24, 2024 10:22 1m 14s
VLlama vision model ISQ support Analysis #1628: Pull request #928 synchronize by EricLBuehler
November 23, 2024 11:00 1m 2s
November 23, 2024 11:00 1m 2s
VLlama vision model ISQ support Analysis #1627: Pull request #928 opened by EricLBuehler
November 23, 2024 03:38 1m 7s
November 23, 2024 03:38 1m 7s
Default to SDPA for faster VLlama PP T/s Analysis #1626: Pull request #927 synchronize by EricLBuehler
November 23, 2024 03:33 59s
November 23, 2024 03:33 59s
Default to SDPA for faster VLlama PP T/s Analysis #1625: Pull request #927 opened by EricLBuehler
November 22, 2024 23:41 59s
November 22, 2024 23:41 59s
Paged Attention alibi support Analysis #1624: Pull request #926 opened by EricLBuehler
November 22, 2024 13:43 1m 2s
November 22, 2024 13:43 1m 2s
Faster CUDA prompt speeds Analysis #1623: Pull request #925 opened by EricLBuehler
November 21, 2024 20:10 17m 33s
November 21, 2024 20:10 17m 33s
Faster CUDA prompt speeds Analysis #1622: Pull request #924 opened by EricLBuehler
November 21, 2024 20:09 12m 36s
November 21, 2024 20:09 12m 36s
Expand attnmask on cuda Analysis #1621: Pull request #923 opened by EricLBuehler
November 21, 2024 18:45 1m 12s
November 21, 2024 18:45 1m 12s
add serde serialization to text chat types Analysis #1620: Pull request #921 synchronize by rozgo
November 20, 2024 23:30 59s
November 20, 2024 23:30 59s
add serde serialization to text chat types Analysis #1619: Pull request #921 opened by rozgo
November 20, 2024 20:35 1m 1s
November 20, 2024 20:35 1m 1s
Dont always compile with fp8, bf16 for cuda Analysis #1618: Pull request #920 opened by EricLBuehler
November 20, 2024 19:36 1m 11s
November 20, 2024 19:36 1m 11s
Experiment with vendoring the Candle fork Analysis #1617: Pull request #919 opened by EricLBuehler
November 20, 2024 00:24 1m 0s
November 20, 2024 00:24 1m 0s
fix(docker): workaround for missing nvidia-smi, bump cuda to current Analysis #1616: Pull request #913 synchronize by pull bot
November 19, 2024 00:45 1m 16s
November 19, 2024 00:45 1m 16s
Fixes for kv cache grow Analysis #1615: Pull request #917 opened by EricLBuehler
November 18, 2024 22:12 1m 2s
November 18, 2024 22:12 1m 2s
Preallocated KV cache Analysis #1614: Pull request #916 synchronize by EricLBuehler
November 18, 2024 18:49 1m 8s
November 18, 2024 18:49 1m 8s
Preallocated KV cache Analysis #1613: Pull request #916 synchronize by EricLBuehler
November 18, 2024 18:31 1m 6s
November 18, 2024 18:31 1m 6s
Preallocated KV cache Analysis #1612: Pull request #916 synchronize by EricLBuehler
November 18, 2024 14:45 1m 1s
November 18, 2024 14:45 1m 1s
Preallocated KV cache Analysis #1611: Pull request #916 synchronize by EricLBuehler
November 18, 2024 14:44 1m 13s
November 18, 2024 14:44 1m 13s
Preallocated KV cache Analysis #1610: Pull request #916 opened by EricLBuehler
November 18, 2024 14:09 1m 8s
November 18, 2024 14:09 1m 8s
Metal: Use mtl resource shared to avoid one copy Analysis #1609: Pull request #914 opened by EricLBuehler
November 17, 2024 01:59 1m 7s
November 17, 2024 01:59 1m 7s