Skip to content

Actions: mlc-ai/mlc-llm

Build Docs

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
428 workflow runs
428 workflow runs
Event

Filter by event

Loading
Status

Filter by status

Loading
Branch
Actor

Filter by actor

Loading
[Fix][Tokenizer] Fix failure in decoding tokens for ByteLevel BPE (#2…
Build Docs #428: Commit 64d8dc6 pushed by tqchen
July 11, 2024 17:23 6m 25s main
July 11, 2024 17:23 6m 25s
[Fix] Fix KV cache single-page copy kernel (#2644)
Build Docs #427: Commit 16a79ab pushed by MasterJH5574
July 11, 2024 14:17 6m 46s main
July 11, 2024 14:17 6m 46s
Fix for RWKV new config and new format vocab (#2632)
Build Docs #426: Commit 7d73cfa pushed by tqchen
July 8, 2024 13:46 6m 51s main
July 8, 2024 13:46 6m 51s
[Model] Support Internlm2.5 (#2630)
Build Docs #425: Commit c7756f9 pushed by MasterJH5574
July 8, 2024 03:56 7m 36s main
July 8, 2024 03:56 7m 36s
[Serving] Merge multiple token embedding lookup into one (#2629)
Build Docs #424: Commit c6122d7 pushed by MasterJH5574
July 8, 2024 03:55 7m 7s main
July 8, 2024 03:55 7m 7s
[SLM] Internlm2 Multi-GPU support (#2626)
Build Docs #423: Commit 5165a58 pushed by MasterJH5574
July 8, 2024 03:55 7m 3s main
July 8, 2024 03:55 7m 3s
[Fix] Fix the chunked prefill condition (#2628)
Build Docs #422: Commit ebf5617 pushed by MasterJH5574
July 5, 2024 18:35 7m 16s main
July 5, 2024 18:35 7m 16s
[Fix] Mark the decode requests in hybrid prefill (#2621)
Build Docs #421: Commit 5b63980 pushed by MasterJH5574
July 4, 2024 04:21 6m 56s main
July 4, 2024 04:21 6m 56s
[Android] Update include path for tvm runtime src (#2616)
Build Docs #420: Commit adc6ee6 pushed by MasterJH5574
July 2, 2024 19:57 7m 25s main
July 2, 2024 19:57 7m 25s
July 2, 2024 15:41 7m 4s
[SLM] Add support for InternLM2 architecture (#2608)
Build Docs #418: Commit 2d32094 pushed by MasterJH5574
July 2, 2024 15:40 7m 11s main
July 2, 2024 15:40 7m 11s
Update debug_compare (#2612)
Build Docs #417: Commit c09b108 pushed by MasterJH5574
July 2, 2024 15:37 7m 15s main
July 2, 2024 15:37 7m 15s
[Fix] Gemma hidden_activation compatibility (#2614)
Build Docs #416: Commit 0575b92 pushed by MasterJH5574
July 1, 2024 21:02 6m 30s main
July 1, 2024 21:02 6m 30s
[Android] Reduce binary size (#2606)
Build Docs #415: Commit fbb6a48 pushed by MasterJH5574
July 1, 2024 19:56 6m 31s main
July 1, 2024 19:56 6m 31s
[Fix] Set the missed prefill finish time (#2613)
Build Docs #414: Commit d911c60 pushed by MasterJH5574
July 1, 2024 16:47 6m 30s main
July 1, 2024 16:47 6m 30s
Update quick_start.rst to fix broken links (#2607)
Build Docs #413: Commit cbf0b02 pushed by tqchen
June 27, 2024 17:45 6m 41s main
June 27, 2024 17:45 6m 41s
[Serving] Hybrid prefill (#2604)
Build Docs #412: Commit 6a48a02 pushed by MasterJH5574
June 25, 2024 21:17 7m 37s main
June 25, 2024 21:17 7m 37s
[Model] Gemma 1.1 compatibility (#2594)
Build Docs #411: Commit 437166a pushed by tqchen
June 19, 2024 18:51 7m 16s main
June 19, 2024 18:51 7m 16s
[Op] Top-4 implementation for MoE model (#2586)
Build Docs #410: Commit e9340c3 pushed by tqchen
June 17, 2024 12:15 6m 51s main
June 17, 2024 12:15 6m 51s
[Doc] Update WebLLM doc (#2578)
Build Docs #409: Commit 75b970b pushed by CharlieFRuan
June 14, 2024 02:22 7m 39s main
June 14, 2024 02:22 7m 39s
[Metrics] Add missing fields in Reset (#2574)
Build Docs #408: Commit ceba951 pushed by tqchen
June 13, 2024 11:30 6m 49s main
June 13, 2024 11:30 6m 49s
[Model] Support Multi-GPU for Qwen-MoE model (#2573)
Build Docs #407: Commit 94a0295 pushed by Hzfengsy
June 13, 2024 05:29 6m 30s main
June 13, 2024 05:29 6m 30s
[Bench] Json mode bench (#2552)
Build Docs #406: Commit 07c92b0 pushed by cyx-6
June 12, 2024 21:21 6m 48s main
June 12, 2024 21:21 6m 48s
[Serving] Apply tree structure in draft token verification (#2563)
Build Docs #405: Commit dcece51 pushed by tqchen
June 12, 2024 11:14 7m 48s main
June 12, 2024 11:14 7m 48s
[Model] Enhance error reporting for invalid tensor-parallel settings …
Build Docs #404: Commit 873827c pushed by tqchen
June 12, 2024 11:14 6m 55s main
June 12, 2024 11:14 6m 55s