68e9d6ab33
feat(server): shard token decode ( #303 )
2023-05-10 15:48:21 +02:00
ad66f6ef9a
feat(server): optim flash causal lm decode_token ( #285 )
2023-05-09 18:26:19 +02:00
b4aa87db58
fea(server): decrease convert RAM requirements ( #286 )
2023-05-05 17:57:02 +02:00
690fc31757
fix(server): fix convert ( #284 )
2023-05-05 15:28:08 +02:00
f08343d44d
fix(server): Removes the parallelism in file convertion (during download) ( #275 )
2023-05-04 15:22:54 +02:00
85aa7e2e7b
feat(server): support hf endpoint weight layout ( #266 )
2023-05-03 11:36:24 +02:00
4096000e34
fix(server): fix typo in tokenizers decode ( #269 )
...
closes #268
2023-05-03 10:10:34 +02:00
f092ba9b22
feat(server): add watermarking tests ( #248 )
2023-04-27 19:16:35 +02:00
b9ae7e5da1
chore(server): update transformers ( #250 )
2023-04-27 09:57:41 +02:00
34bca0b8d3
fix(server): Small tidy of code from recent changes ( #251 )
...
remaining_decode_tokens was calculated twice in Seq2SeqLMBatch.filter()
2023-04-27 09:57:28 +02:00
b4cf832c40
fix(server): fix reshaping of bloom past_key_values in concatenate() ( #252 )
...
Introduced in #214
Fixes #249
2023-04-27 09:51:27 +02:00
db2b4e0754
feat(router): new healthcheck that skips the queue ( #244 )
...
Co-authored-by: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com>
Co-authored-by: OlivierDehaene <olivier@huggingface.co>
2023-04-26 20:23:54 +02:00
37b64a5c10
chore(server): update safetensors version ( #235 )
2023-04-25 13:50:56 +02:00
ebc74d5666
feat(router): use number of tokens in batch as input for dynamic batching ( #226 )
...
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2023-04-24 17:59:00 +02:00
98a3e0d135
chore(server): update huggingface-hub ( #227 )
2023-04-24 15:57:13 +02:00
4a7dd4085a
feat(server): reduce memory requirement ( #214 )
2023-04-24 14:15:42 +02:00
6ded76a4ae
v0.6.0 ( #222 )
2023-04-21 21:00:57 +02:00
4b460e72fb
fix(server): fix flash batch filtering ( #220 )
2023-04-21 20:26:01 +02:00
1ffea36ec2
fix(server): fix flash causal ( #219 )
2023-04-21 19:49:08 +02:00
86bca365df
fix(server): fix flash causal ( #218 )
2023-04-21 19:42:16 +02:00
afc5b999d0
fix(server): cleanup new flash past_key_values logic ( #217 )
2023-04-21 16:19:04 +02:00
db4cb5e4ed
fix(server): fix past key values logic ( #216 )
...
@njhill fyi
2023-04-21 15:59:18 +02:00
343437c7b5
feat(router): add device and dtype info ( #215 )
2023-04-21 15:36:29 +02:00
ac8c0f6fe4
feat(server): flash attention past key value optimizations ( #213 )
2023-04-21 14:57:18 +02:00
709d8936f6
feat(router): drop requests when client closes the channel ( #202 )
2023-04-20 11:07:40 +02:00
b6ee0ec7b0
feat(router): add git sha to info route ( #208 )
2023-04-19 21:36:59 +02:00
6837b2eb77
fix(docker): remove unused dependencies ( #205 )
2023-04-19 19:39:31 +02:00
5d27f5259b
fix(server): fix hf_transfer issue with private repos ( #203 )
2023-04-19 17:36:16 +02:00
a88c54bb4c
feat(server): check cuda capability when importing flash models ( #201 )
...
close #198
2023-04-19 12:52:37 +02:00
e14ae3b5e9
feat(server): support quantization for flash models ( #200 )
...
closes #197
2023-04-19 12:51:11 +02:00
7a1ba58557
fix(docker): fix docker image dependencies ( #187 )
2023-04-17 00:26:47 +02:00
53ee09c0b0
fea(dockerfile): better layer caching ( #159 )
2023-04-14 10:12:21 +02:00
64347b05ff
fix(ci): fix CVE in github-slug-action ( #174 )
2023-04-13 12:43:05 +02:00
880a76eed5
feat(server): support sharded santacoder ( #167 )
2023-04-12 17:18:08 +02:00
5fa8ae041c
feat(server): optimize decode for sane tokenizers ( #170 )
2023-04-12 12:03:10 +02:00
6f0f1d70f6
v0.5.0 ( #168 )
2023-04-11 20:32:18 +02:00
f26dfd0dc1
feat(server): support OPT models ( #55 )
...
OPT models do not all have a `tokenizer.json` file on the hub at the
moment. Can't merge for now.
2023-04-11 19:16:41 +02:00
299217c95c
feat(server): add flash attention llama ( #144 )
2023-04-11 16:38:22 +02:00
9987960062
feat(router): make router input validation optional ( #164 )
2023-04-09 20:22:27 +02:00
1883d8ecde
feat(docker): improve flash_attention caching ( #160 )
2023-04-09 19:59:16 +02:00
3f2542bb6a
fix(server): fix escape characters in stop sequence ( #155 )
2023-04-05 19:37:41 +02:00
c0aeb32583
feat(server): flash santacoder ( #153 )
2023-04-03 19:06:42 +02:00
fef1a1c381
v0.4.3 ( #152 )
2023-03-30 17:28:14 +02:00
84722f3e33
v0.4.2 ( #151 )
2023-03-30 17:10:01 +02:00
08b7e4a282
fix(server): fix flash neox rotary embeddings ( #150 )
2023-03-30 16:12:23 +02:00
610bb1f978
feat(benchmark): tui based benchmarking tool ( #149 )
2023-03-30 15:26:27 +02:00
c9bdaa8b73
feat(server): reduce mlp and attn in one op for flash neox ( #145 )
2023-03-28 16:51:41 +02:00
f000068944
feat(server): clear cache on error ( #143 )
2023-03-28 11:29:35 +02:00
8e8dd984d8
feat(server): Add mypy-protobuf ( #141 )
...
Generates .pyi files for protobuf stubs which provide strong typing
information. Very helpful for IDE auto-completion, etc.
2023-03-27 09:25:15 +02:00
462530c2b0
fix(server): Avoid using try/except to determine kind of AutoModel ( #142 )
2023-03-27 09:23:22 +02:00
ab5fd8cf93
v0.4.1 ( #140 )
2023-03-26 16:37:51 +02:00
678b2f3900
feat(server): cleanup flash neox loading ( #139 )
2023-03-26 16:37:21 +02:00
d6a93fe992
fix(server): fix flash-neox scores warping ( #137 )
2023-03-24 18:21:41 +01:00
05e9a796cc
feat(server): flash neoX ( #133 )
2023-03-24 14:02:14 +01:00
b49dbf2d88
fix(server): use server tokenizer as gt ( #128 )
2023-03-16 12:12:26 +01:00
8ad60b752f
fix(server): add position ids to neox ( #126 )
2023-03-15 13:12:49 +01:00
cbd36aa4d1
fix(server): revert gpt-neox optims ( #123 )
2023-03-13 22:57:08 +01:00
411d6247f4
v0.4.0 ( #119 )
2023-03-09 16:07:01 +01:00
c0795de2f2
fix(server): do not warp prefill logits ( #116 )
2023-03-09 13:00:10 +01:00
1a2d68250a
feat: support typical sampling ( #114 )
...
closes #112
2023-03-09 11:33:57 +01:00
941cd42e0c
fix(server): fix index out of range for watermarking ( #110 )
2023-03-08 18:29:08 +01:00
b1485e18c5
fix(server): fix galactica batch ( #106 )
...
closes #105
2023-03-07 20:05:21 +01:00
3fef90d50f
feat(clients): Python client ( #103 )
2023-03-07 18:52:22 +01:00
cd5961b5da
feat: allow local models ( #101 )
...
closes #99
2023-03-06 14:39:36 +01:00
9b205d33cc
fix(server): fix generate_stream by forcing tokens to be decoded correctly ( #100 )
2023-03-06 13:22:58 +01:00
1c19b0934e
v0.3.2 ( #97 )
2023-03-03 18:42:20 +01:00
0b6807caa4
feat(server): fix transformers commit ( #96 )
2023-03-03 17:56:27 +01:00
2d39f199ae
feat(server): update to hf_transfer==0.1.2 ( #93 )
2023-03-03 11:26:27 +01:00
9b8ea6a6c7
feat(server): add logits watermark ( #90 )
2023-03-02 12:30:41 +01:00
65e2f1624e
fix(server): fix token_is_special ( #87 )
2023-02-24 17:20:00 +01:00
0ac184ce77
feat(server): add special token bool ( #85 )
2023-02-24 15:55:57 +01:00
4b1c9720c0
v0.3.1 ( #84 )
2023-02-24 13:27:41 +01:00
44ce098c10
feat(server): pre-allocate max attention mask ( #75 )
2023-02-24 12:49:21 +01:00
78063c0569
fix(server): remove position_ids from galactica forward ( #82 )
...
closes #80
2023-02-20 19:28:57 +01:00
17bc841b1b
feat(server): enable hf-transfer ( #76 )
2023-02-18 14:04:11 +01:00
c720555adc
v0.3.0 ( #72 )
2023-02-16 17:28:29 +01:00
439fcaf810
feat(router): add prometheus metrics scrape endpoint ( #71 )
2023-02-16 17:18:53 +01:00
c5a4a1faf3
feat(server): improve download logging ( #66 )
2023-02-15 16:11:32 +01:00
0fbc691946
feat: add safetensors conversion ( #63 )
2023-02-14 13:02:16 +01:00
9af454142a
feat: add distributed tracing ( #62 )
2023-02-13 13:02:45 +01:00
1ad3250b89
fix(docker): increase shm size ( #60 )
2023-02-08 17:53:33 +01:00
c503a639b1
feat(server): support t5 ( #59 )
2023-02-07 18:25:17 +01:00
2fe5e1b30e
V0.2.1 ( #58 )
2023-02-07 15:40:25 +01:00
4acc42a605
fix(server): better handling of inference mode ( #57 )
2023-02-07 15:38:22 +01:00
20c3c5940c
feat(router): refactor API and add openAPI schemas ( #53 )
2023-02-03 12:43:37 +01:00
b1482d9048
breaking(router): modify /generate API to only return generated text ( #50 )
...
@njhill, @yk FYI
generated_text was concatenated to the user prompt for legacy reason. We
want to remove this behaviour as we don't think it is useful and even
detrimonial to usability.
We also remove the unused Vec.
2023-02-02 15:02:04 +01:00
df227ac20d
fix(server): allow greedy repetition penalty ( #51 )
2023-02-02 10:34:35 +01:00
775115e3a5
feat(server): allow the server to use a local weight cache ( #49 )
2023-02-01 16:22:10 +01:00
313194f6d7
feat(server): support repetition penalty ( #47 )
2023-02-01 15:58:42 +01:00
2ad895a6cc
feat(server): allow gpt-neox models with odd vocab sizes to be sharded ( #48 )
2023-02-01 14:43:59 +01:00
f830706b21
feat(server): Support GPT-Neox ( #39 )
2023-01-31 18:53:56 +01:00
c6e8b9442b
fix(server): fix quantization for sharded models ( #45 )
2023-01-31 17:40:38 +01:00
017a2a8c2f
feat: Add token streaming using ServerSideEvents support ( #41 )
2023-01-31 17:04:00 +01:00
54fec93193
fix(server): fix seeding with multiple shards ( #44 )
2023-01-31 16:01:15 +01:00
03bdf18290
fix(server): fix seeding on gpu ( #42 )
2023-01-31 14:30:33 +01:00
4f9ac67cfa
Revert "feat: Add token streaming using ServerSideEvents support" ( #40 )
...
Reverts huggingface/text-generation-inference#36
2023-01-31 14:21:51 +01:00
7fbfbb0dc5
feat: Add token streaming using ServerSideEvents support ( #36 )
...
Add token streaming using ServerSideEvents (SSE).
The signature of the SSE events is:
```rust
struct Details {
finish_reason: String,
generated_tokens: u32,
seed: Option<u64>,
}
struct StreamResponse {
token: Token,
generated_text: Option<String>,
details: Option<Details>,
}
struct ErrorResponse {
error: String,
}
```
2023-01-31 11:49:43 +01:00
cd298bc5e5
feat: Support sampling seeding ( #37 )
...
Co-authored-by: Yannic Kilcher <yk@users.noreply.github.com>
2023-01-30 15:36:16 +01:00
ce960be0a5
feat(bloom): use torch.nn.Linear and torch.nn.GELU ( #33 )
2023-01-26 15:33:45 +01:00
13e7044ab7
fix(dockerfile): fix docker build ( #32 )
2023-01-24 19:52:39 +01:00
OlivierDehaene