Skip to content

Actions: vectorch-ai/ScaleLLM

Format

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
718 workflow runs
718 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[fix] put finish reason into a separate response
Format #45: Pull request #119 opened by guocuimi
April 6, 2024 02:20 19s response
April 6, 2024 02:20 19s
[feat] cancel request if rpc is not ok
Format #44: Pull request #118 synchronize by guocuimi
April 5, 2024 07:49 17s cancel
April 5, 2024 07:49 17s
[feat] cancel request if rpc is not ok
Format #43: Pull request #118 opened by guocuimi
April 5, 2024 07:46 56s cancel
April 5, 2024 07:46 56s
[feat] enable speculative decoding for scalellm.
Format #42: Pull request #117 synchronize by guocuimi
April 5, 2024 05:33 17s enable
April 5, 2024 05:33 17s
[feat] enable speculative decoding for scalellm.
Format #41: Pull request #117 synchronize by guocuimi
April 5, 2024 05:31 21s enable
April 5, 2024 05:31 21s
[feat] enable speculative decoding for scalellm.
Format #40: Pull request #117 synchronize by guocuimi
April 5, 2024 05:28 18s enable
April 5, 2024 05:28 18s
[feat] enable speculative decoding for scalellm.
Format #39: Pull request #117 opened by guocuimi
April 5, 2024 05:27 23s enable
April 5, 2024 05:27 23s
[feat] added stream support for n > 1 scenarios
Format #38: Pull request #116 opened by guocuimi
April 4, 2024 08:06 36s stream
April 4, 2024 08:06 36s
[feat] added sampling support for multiple query decoding
Format #37: Pull request #115 synchronize by guocuimi
April 4, 2024 04:16 17s multi_query
April 4, 2024 04:16 17s
[feat] added sampling support for multiple query decoding
Format #36: Pull request #115 opened by guocuimi
April 4, 2024 03:14 19s multi_query
April 4, 2024 03:14 19s
[feat] mask out rejected tokens with -1 in Rejection Sampler
Format #35: Pull request #114 synchronize by guocuimi
April 3, 2024 06:08 19s mask
April 3, 2024 06:08 19s
[feat] mask out rejected tokens with -1 in Rejection Sampler
Format #34: Pull request #114 opened by guocuimi
April 3, 2024 06:06 18s mask
April 3, 2024 06:06 18s
[feat] enable speculative decoding for simple server
Format #33: Pull request #113 synchronize by guocuimi
April 2, 2024 05:17 20s enable_spec
April 2, 2024 05:17 20s
[feat] enable speculative decoding for simple server
Format #32: Pull request #113 synchronize by guocuimi
April 2, 2024 03:48 17s enable_spec
April 2, 2024 03:48 17s
[feat] enable speculative decoding for simple server
Format #31: Pull request #113 opened by guocuimi
April 1, 2024 18:14 37s enable_spec
April 1, 2024 18:14 37s
[feat] added rejection sampler for speculative decoding.
Format #30: Pull request #112 synchronize by guocuimi
March 30, 2024 19:18 18s sampler
March 30, 2024 19:18 18s
[feat] added rejection sampler for speculative decoding.
Format #29: Pull request #112 synchronize by guocuimi
March 30, 2024 19:16 17s sampler
March 30, 2024 19:16 17s
[feat] added rejection sampler for speculative decoding.
Format #28: Pull request #112 synchronize by guocuimi
March 30, 2024 19:05 17s sampler
March 30, 2024 19:05 17s
[feat] added rejection sampler for speculative decoding.
Format #27: Pull request #112 synchronize by guocuimi
March 30, 2024 18:53 15s sampler
March 30, 2024 18:53 15s
[feat] added rejection sampler for speculative decoding.
Format #26: Pull request #112 synchronize by guocuimi
March 30, 2024 18:46 22s sampler
March 30, 2024 18:46 22s
[feat] added rejection sampler for speculative decoding.
Format #24: Pull request #112 synchronize by guocuimi
March 30, 2024 07:14 17s sampler
March 30, 2024 07:14 17s
[feat] added rejection sampler for speculative decoding.
Format #23: Pull request #112 synchronize by guocuimi
March 30, 2024 06:58 15s sampler
March 30, 2024 06:58 15s
[feat] added rejection sampler for speculative decoding.
Format #22: Pull request #112 synchronize by guocuimi
March 30, 2024 06:50 16s sampler
March 30, 2024 06:50 16s
[feat] added rejection sampler for speculative decoding.
Format #21: Pull request #112 opened by guocuimi
March 30, 2024 06:27 30s sampler
March 30, 2024 06:27 30s
ProTip! You can narrow down the results and go further in time using created:<2024-03-30 or the other filters available.