Skip to content

Actions: Tencent/AngelSlim

Actions

Build and Deploy Documentation

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
deploy.yml
76 workflow runs
76 workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
fix: update qwen3_omni with transformers>=5.0 (#296) Build and Deploy Documentation #76: Commit f76d316 pushed by ali-88123
46s main
main
46s
update readme (#293) Build and Deploy Documentation #75: Commit c76d35e pushed by yghstill
46s main
main
46s
Update the Figure in the 2bit/1.25bit (#292) Build and Deploy Documentation #74: Commit 15c48de pushed by yghstill
48s main
main
48s
Support QAT with deepspeed zero3 and gradient checkpoint (#290) Build and Deploy Documentation #73: Commit 7e4ffbc pushed by yghstill
38s main
main
38s
Add contents for the Hy-MT1.5-1.8B-1.25bit and Hy-MT1.5-1.8B-2bit Mod… Build and Deploy Documentation #72: Commit db94e50 pushed by yghstill
48s main
main
48s
feat: add Stem sparse attention module (#286) Build and Deploy Documentation #71: Commit 3a9c1a3 pushed by yghstill
33s main
main
33s
feat(qat): add lwc and distillation loss (#285) Build and Deploy Documentation #70: Commit 90209c2 pushed by yghstill
35s main
main
35s
feat(qat): add KV cache quantization support in QAT pipeline (#284) Build and Deploy Documentation #69: Commit 43a322a pushed by ali-88123
48s main
main
48s
feat(token_compressor): introduce universal pruning framework and ali… Build and Deploy Documentation #68: Commit 0f1e8a6 pushed by yghstill
38s main
main
38s
fix(speculative): fix qwen3/qwen2.5 (#280) Build and Deploy Documentation #67: Commit c5c8186 pushed by yghstill
35s main
main
35s
feat(speculative): support extract hidden states with vllm backend (#… Build and Deploy Documentation #66: Commit de4f5ec pushed by yghstill
36s main
main
36s
[fix]: Fix reference for weights to quant. (#276) Build and Deploy Documentation #65: Commit b0af806 pushed by yghstill
33s main
main
33s
[ref]: Refeactor weight-only quantization. (#275) Build and Deploy Documentation #64: Commit 8f66b65 pushed by yghstill
31s main
main
31s
feat(spinquant): refactor SpinQuant with CPU offload, parallel fuse, … Build and Deploy Documentation #63: Commit 99efb57 pushed by gavingavin99
38s main
main
38s
feat: add QAT pipline (#265) Build and Deploy Documentation #62: Commit 028f7ab pushed by ali-88123
34s main
main
34s
support eagle3 offline training with per_device_train_batch_size>1 (#… Build and Deploy Documentation #61: Commit 676ae7d pushed by irisliu10
38s main
main
38s
add generate_vlm_hidden_for_draft_model_batch.sh for vlm (#247) Build and Deploy Documentation #60: Commit 0f7df68 pushed by irisliu10
35s main
main
35s
update readme and code format (#243) Build and Deploy Documentation #59: Commit 3bbee0a pushed by yghstill
41s main
main
41s
fix vlm dataset processor with no_padding formate (#224) Build and Deploy Documentation #58: Commit 8e66c0e pushed by irisliu10
33s main
main
33s
support qwen2.5 eagle3 training (#220) Build and Deploy Documentation #57: Commit 5c9955e pushed by liusong1222
34s main
main
34s
modify audio_tts_eagle.md (#205) Build and Deploy Documentation #56: Commit ebfe17c pushed by ali-88123
29s main
main
29s
fix bug in readme & update index.md of do (#202) Build and Deploy Documentation #55: Commit 823bdfb pushed by yghstill
32s main
main
32s
update vlm & audio eagle3 doc & readme (#201) Build and Deploy Documentation #54: Commit 6966570 pushed by irisliu10
36s main
main
36s
Feature: support Qwen2_audio eagle3 speculative decoding (#199) Build and Deploy Documentation #53: Commit 61f206a pushed by irisliu10
42s main
main
42s
fix speculative decoding benchmark data (#195) Build and Deploy Documentation #52: Commit d43bcbc pushed by yghstill
40s main
main
40s