Skip to content

Actions: ModelTC/lightllm

Actions

All workflows

Actions

Loading...

Showing runs from all workflows
173 workflow runs
173 workflow runs
Event

Filter by event

Status

Filter by status

Branch
Actor

Filter by actor

Compat generate api (#414)
Docker #173: Commit 483fc89 pushed by hiworldwzj
May 27, 2024 03:50 2m 5s main
May 27, 2024 03:50 2m 5s
Dynamic img token (#413)
Docker #172: Commit 06545e7 pushed by hiworldwzj
May 24, 2024 08:17 1m 56s main
May 24, 2024 08:17 1m 56s
Add tokens http interface (#412)
Docker #171: Commit 53f65ef pushed by hiworldwzj
May 20, 2024 09:43 4m 12s main
May 20, 2024 09:43 4m 12s
fix bug for w8a8 mode (#411)
Docker #170: Commit a775bd3 pushed by hiworldwzj
May 20, 2024 08:29 1m 54s main
May 20, 2024 08:29 1m 54s
May 15, 2024 08:20 27m 51s
bf16 compatibility for omitted kernel (#396)
Docker #168: Commit 4b037f6 pushed by hiworldwzj
April 15, 2024 03:05 3m 2s main
April 15, 2024 03:05 3m 2s
remove the support for triton==2.0.0 (#395)
Docker #167: Commit bcb3212 pushed by shihaobai
April 12, 2024 10:19 1m 52s main
April 12, 2024 10:19 1m 52s
Fix CI (#392)
Docker #166: Commit 390ac96 pushed by llehtahw
April 11, 2024 09:30 2m 3s main
April 11, 2024 09:30 2m 3s
fix input_embdings.dtype=None.dtype (#390)
Docker #165: Commit aa2b655 pushed by WANDY666
April 11, 2024 07:15 2m 21s main
April 11, 2024 07:15 2m 21s
Add bf16 inference for llm model (#387)
Docker #164: Commit 15a050a pushed by hiworldwzj
April 10, 2024 14:28 2m 5s main
April 10, 2024 14:28 2m 5s
April 9, 2024 13:13 2m 6s
support llama-quik, a w4a4 quantization method (#386)
Docker #162: Commit 8e34dad pushed by hiworldwzj
April 8, 2024 03:03 2m 7s main
April 8, 2024 03:03 2m 7s
add min_new_tokens sampling parameter (#384)
Docker #161: Commit a231505 pushed by hiworldwzj
April 1, 2024 03:37 3m 17s main
April 1, 2024 03:37 3m 17s
w6a16 mode (#382)
Docker #160: Commit 7cd10a0 pushed by hiworldwzj
March 29, 2024 01:31 1m 50s main
March 29, 2024 01:31 1m 50s
fix eos_id default value to [2] (#378)
Docker #159: Commit 78047d1 pushed by hiworldwzj
March 26, 2024 09:43 2m 0s main
March 26, 2024 09:43 2m 0s
March 26, 2024 09:37 2m 11s
Update model.py To Fix ntk length bug. (#375)
Docker #157: Commit aa98b35 pushed by hiworldwzj
March 26, 2024 07:06 7m 30s main
March 26, 2024 07:06 7m 30s
reset the ntk length range (#374)
Docker #156: Commit f5dc783 pushed by shihaobai
March 25, 2024 12:00 3m 59s main
March 25, 2024 12:00 3m 59s
March 21, 2024 08:53 1m 50s
Bug Fix #368 (#370)
Docker #154: Commit c3dc640 pushed by hiworldwzj
March 21, 2024 07:51 2m 52s main
March 21, 2024 07:51 2m 52s
add cuda int4kv copy kernel (#369)
Docker #153: Commit c5d6794 pushed by hiworldwzj
March 21, 2024 05:57 4m 19s main
March 21, 2024 05:57 4m 19s
fix: b_ready_cache_len default value (#366)
Docker #152: Commit 9fed5e9 pushed by hiworldwzj
March 20, 2024 09:21 3m 38s main
March 20, 2024 09:21 3m 38s
add mode ppl_int4kv_flashdecoding (#367)
Docker #151: Commit 859a48b pushed by hiworldwzj
March 20, 2024 08:58 2m 27s main
March 20, 2024 08:58 2m 27s
fix issue #357 (#365)
Docker #150: Commit 986f93d pushed by hiworldwzj
March 19, 2024 09:26 3m 20s main
March 19, 2024 09:26 3m 20s
March 19, 2024 06:51 2m 16s