Woosuk Kwon
|
025a32f9ed
|
[Model Runner V2] Remove async barrier (#32083)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2026-01-11 20:24:30 -08:00 |
|
Woosuk Kwon
|
19504ac07f
|
[Model Runner V2] Skip building deprecated fields in attn metadata (#32132)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2026-01-11 14:31:04 -08:00 |
|
Woosuk Kwon
|
cc050558f4
|
[Model Runner V2] Implement get_num_sampled_and_rejected kernel (#30029)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-12-04 07:19:42 -08:00 |
|
Cyrus Leung
|
64bc09ba27
|
[Core] Enable inputs_embeds_size separate from hidden_size (#29741)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-11-30 17:31:12 +08:00 |
|
Woosuk Kwon
|
6afc0ffaf6
|
[Model Runner V2] Add sample/ directory and reorganize files (#29719)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-11-29 00:41:01 -08:00 |
|
Woosuk Kwon
|
ca1b1e7296
|
[Model Runner V2] Refactor prefill token preparation (#29712)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-11-28 19:49:17 -08:00 |
|
Cyrus Leung
|
e6d4f3c254
|
[Bugfix] Fix pre-commit (#29601)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-11-27 02:23:06 -08:00 |
|
Woosuk Kwon
|
da3222f371
|
[Model Runner V2] Implement multi-step Eagle with CUDA graph (#29559)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-11-27 00:09:41 -08:00 |
|
Woosuk Kwon
|
f32c7d6f54
|
[Model Runner V2] Simplify Eagle bookkeeping with num_rejected (#29347)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-11-24 13:54:59 -08:00 |
|
Woosuk Kwon
|
97588c4d12
|
[Model Runner V2] Add minor clarification comments for Eagle (#29332)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-11-24 11:28:56 -08:00 |
|
Woosuk Kwon
|
cc313cb73d
|
[Model Runner V2] Implement Single-step Eagle 1 (#29300)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-11-24 09:32:27 -08:00 |
|
Woosuk Kwon
|
b004c00418
|
[Model Runner V2] Support spec decoding [1/N] (#29274)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-11-23 10:09:06 -08:00 |
|