Bryan Lu
70788bdbdc
[V1][Spec Decode] Apply torch.compile & cudagraph to EAGLE ( #17211 )
...
Signed-off-by: Bryan Lu <yuzhelu@amazon.com>
2025-04-29 21:10:00 +00:00
Ekagra Ranjan
e136000595
[V1][Spec Decode] Make Eagle model arch config driven ( #17323 )
2025-04-29 10:22:02 +08:00
Benjamin Chislett
a0e619e62a
[V1][Spec Decode] EAGLE-3 Support ( #16937 )
...
Signed-off-by: Bryan Lu <yuzhelu@amazon.com>
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
Co-authored-by: Bryan Lu <yuzhelu@amazon.com>
2025-04-25 15:43:07 -07:00
Mark McLoughlin
340d7b1b21
[V1][Spec Decoding] Add num_drafts and num_accepted_tokens_per_position metrics ( #16665 )
...
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
2025-04-24 08:57:40 -07:00
Woosuk Kwon
41fb013d29
[V1][Spec Decode] Always use argmax for sampling draft tokens ( #16899 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-04-23 14:57:43 -07:00
Woosuk Kwon
1311913f55
[BugFix][Spec Decode] No in-place update to draft probs ( #16952 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-04-21 19:54:19 -07:00
Woosuk Kwon
3a0fba5cf4
[V1][Spec Decode] Handle draft tokens beyond max_model_len ( #16087 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-04-21 12:38:50 -07:00
Russell Bryant
9dbf7a2dc1
[V1] Remove log noise when idle ( #16735 )
...
Signed-off-by: Russell Bryant <rbryant@redhat.com>
2025-04-16 21:34:08 -07:00
Lily Liu
e8224f3dca
[V1][Spec Decode] Eagle Model loading ( #16035 )
...
Signed-off-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
2025-04-10 11:21:48 -07:00
Woosuk Kwon
63375f0cdb
[V1][Spec Decode] Update N-gram Proposer Interface ( #15750 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-04-04 16:32:54 -07:00
Woosuk Kwon
274d8e8818
[V1][Minor] Enhance SpecDecoding Metrics Log in V1 ( #15902 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-04-01 23:38:02 -07:00
Ekagra Ranjan
24b7fb455a
[Spec Decode] Fix input triton kernel for eagle ( #15909 )
2025-04-01 18:15:14 -07:00
Woosuk Kwon
e75a6301bd
[V1][Spec Decode] Implement Eagle Proposer [1/N] ( #15729 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-04-01 12:33:16 -07:00
Mark McLoughlin
a79cc68b3a
[V1][Metrics] Initial speculative decoding metrics ( #15151 )
...
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
2025-04-01 10:45:04 -07:00
Woosuk Kwon
ebcebeeb6b
[V1][Spec Decode] Enable spec decode for top-p & top-k sampling ( #15063 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-03-24 17:16:46 -07:00
Woosuk Kwon
b9bd76ca14
[V1][Spec Decode] Respect prompt_lookup_max ( #15348 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-03-23 10:41:44 -07:00
Woosuk Kwon
99abb8b650
[V1][Spec Decode] Optimize Rejection Sampler with Triton Kernels ( #14930 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-03-18 14:31:54 -07:00
Lily Liu
8d6cf89526
[V1] [Spec Decode] Support random sampling for spec decode ( #13933 )
...
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-03-16 22:00:20 -07:00
Woosuk Kwon
4c82229898
[V1][Spec Decode] Optimize N-gram matching with Numba ( #13365 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-02-18 13:19:58 -08:00
Woosuk Kwon
cd4a72a28d
[V1][Spec decode] Move drafter to model runner ( #13363 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-02-17 15:40:12 -08:00
Woosuk Kwon
7b89386553
[V1][BugFix] Add __init__.py to v1/spec_decode/ ( #13359 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-02-16 09:39:08 -08:00
Lily Liu
80f63a3966
[V1][Spec Decode] Ngram Spec Decode ( #12193 )
...
Signed-off-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
2025-02-15 18:05:11 -08:00