Skip to content

Actions: mlc-ai/mlc-llm

Build Docs

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
624 workflow runs
624 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[Serve] Separate callback invocation to another thread in AsyncEngine…
Build Docs #49: Commit 522db05 pushed by tqchen
March 29, 2024 05:39 2m 17s main
March 29, 2024 05:39 2m 17s
Update huggingface_loader.py
Build Docs #48: Commit 2b82091 pushed by tqchen
March 28, 2024 13:31 2m 8s main
March 28, 2024 13:31 2m 8s
[Serving] Support NVTX for benchmarking (#2043)
Build Docs #47: Commit 4255a45 pushed by tqchen
March 28, 2024 13:27 7m 0s main
March 28, 2024 13:27 7m 0s
[Model] Skip TVMSynchronize when tracing is not enabled (#2041)
Build Docs #46: Commit cf8d458 pushed by tqchen
March 28, 2024 12:17 2m 35s main
March 28, 2024 12:17 2m 35s
[SLM] Baichuan Multi-GPU support (#2037)
Build Docs #45: Commit a0c0f21 pushed by MasterJH5574
March 28, 2024 03:54 2m 2s main
March 28, 2024 03:54 2m 2s
[Preshard] apply presharding after quantization (#2039)
Build Docs #44: Commit 5ebcda1 pushed by MasterJH5574
March 28, 2024 02:44 2m 32s main
March 28, 2024 02:44 2m 32s
[Model] Add missing broadcast of logit_position for multigpu (#2040)
Build Docs #43: Commit be42bec pushed by MasterJH5574
March 28, 2024 02:43 2m 15s main
March 28, 2024 02:43 2m 15s
[Pipeline] Defer GPU IPC memory lowering (#2038)
Build Docs #42: Commit 2d68e64 pushed by tqchen
March 27, 2024 21:46 2m 7s main
March 27, 2024 21:46 2m 7s
[LLaVa] Follow-up for TODOs in LLaVa model (#2010)
Build Docs #41: Commit 47c8350 pushed by anibohara2000
March 27, 2024 15:09 2m 6s main
March 27, 2024 15:09 2m 6s
[Compiler] Support AUTO mode for all-reduce strategy (#2034)
Build Docs #40: Commit 0a23af5 pushed by tqchen
March 27, 2024 05:38 1m 59s main
March 27, 2024 05:38 1m 59s
[Serving][Grammar] Integration of JSON schema generation (#2030)
Build Docs #39: Commit f2518ab pushed by MasterJH5574
March 27, 2024 03:51 2m 12s main
March 27, 2024 03:51 2m 12s
[Quantization] Skip MoE gate layer (#2012)
Build Docs #38: Commit a6d31d7 pushed by tqchen
March 26, 2024 20:28 2m 19s main
March 26, 2024 20:28 2m 19s
[Serving][Fix] Fix problems in PopenServer (#2032)
Build Docs #37: Commit 8796fb4 pushed by MasterJH5574
March 26, 2024 20:25 2m 50s main
March 26, 2024 20:25 2m 50s
Register stablelm-2 conversation template (#2029)
Build Docs #36: Commit 1c975de pushed by rickzx
March 25, 2024 16:15 2m 15s main
March 25, 2024 16:15 2m 15s
more info for preshard (#2027)
Build Docs #35: Commit f04cd3e pushed by tqchen
March 25, 2024 12:28 2m 49s main
March 25, 2024 12:28 2m 49s
[SLM] Qwen2 Multi-GPU support (#1985)
Build Docs #34: Commit ab9fa81 pushed by tqchen
March 25, 2024 12:22 2m 43s main
March 25, 2024 12:22 2m 43s
Remove unstable assertion in KV cache creation dispatch (#2017)
Build Docs #33: Commit a6de1ff pushed by MasterJH5574
March 24, 2024 18:47 2m 4s main
March 24, 2024 18:47 2m 4s
[iOS] Fix typo in prepare_model_lib.py (#2013)
Build Docs #32: Commit 10f2d00 pushed by MasterJH5574
March 24, 2024 17:30 2m 20s main
March 24, 2024 17:30 2m 20s
[Fix] Fix KV cache creation pass after nn.Module changes (#2011)
Build Docs #31: Commit 837ee53 pushed by MasterJH5574
March 24, 2024 00:54 2m 14s main
March 24, 2024 00:54 2m 14s
Fix invalid use of dataflow var in sampler output (#2003)
Build Docs #30: Commit 64badb5 pushed by vinx13
March 22, 2024 22:48 2m 13s main
March 22, 2024 22:48 2m 13s
[Model] Fix the top-k TIR script for well-formedness (#2002)
Build Docs #29: Commit 8405cb1 pushed by tqchen
March 22, 2024 14:00 2m 9s main
March 22, 2024 14:00 2m 9s
[Compiler] Support IPC memory and customized all-reduce kernels (#1990)
Build Docs #28: Commit 0772940 pushed by tqchen
March 22, 2024 02:22 2m 52s main
March 22, 2024 02:22 2m 52s
[Serve] add allocator in Storage as the upstream change (#1997)
Build Docs #27: Commit 96d9c8b pushed by MasterJH5574
March 21, 2024 21:02 1m 58s main
March 21, 2024 21:02 1m 58s
March 21, 2024 20:45 2m 4s
[Attn] Fix the construction of attn result merge kernel (#1995)
Build Docs #25: Commit 244c2e7 pushed by MasterJH5574
March 21, 2024 20:36 2m 6s main
March 21, 2024 20:36 2m 6s
ProTip! You can narrow down the results and go further in time using created:<2024-03-21 or the other filters available.