alihan/llm-text-generation-inference
1
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2023-08-15 01:09:35 +03:00
Code Issues Packages Projects Releases Wiki Activity
384 Commits 22 Branches 22 Tags

Default Branch

main

05dd14fdb9 · Fix tokenizers==0.13.4 . (#838) · Updated 2023-08-14 20:26:19 +03:00
 ZIP  TAR.GZ

Branches

idefics

5fa4676221 · Tp ready. · Updated 2023-08-14 20:05:21 +03:00
1
2
 ZIP  TAR.GZ
fix_leak

89a4e723d2 · Attempting to fix torch leak. · Updated 2023-08-12 10:06:49 +03:00
7
1
 ZIP  TAR.GZ
streaming_conceptual

4a9615e8ff · Add to ToC · Updated 2023-08-11 16:05:10 +03:00
10
2
 ZIP  TAR.GZ
test_docs

43ed6c217a · Dummy commit · Updated 2023-08-10 11:33:52 +03:00
15
1
 ZIP  TAR.GZ
osanseviero-patch-1

4ddb6681ac · Add workflow to upload documentation · Updated 2023-08-08 08:49:45 +03:00
18
1
 ZIP  TAR.GZ
model_compat_log

e994ad1172 · Added InferenceClient · Updated 2023-08-02 17:57:01 +03:00
32
11
 ZIP  TAR.GZ
compat_logger

7766fee9b1 · fix typo for dynamic rotary (#745) · Updated 2023-07-31 19:58:46 +03:00
26
0
 Included
 ZIP  TAR.GZ
dev

66cea49d57 · Cargo fmt · Updated 2023-07-31 11:04:25 +03:00
33
2
 ZIP  TAR.GZ
simpler_exllama

f555dabca8 · Putting back header inclusion (seems unused but still) · Updated 2023-07-20 18:46:51 +03:00
53
21
 ZIP  TAR.GZ
bnb4

bfa3920aec · BNB 4bits. · Updated 2023-07-12 15:42:43 +03:00
79
7
 ZIP  TAR.GZ
enable_non_divisible_embeddings

db4efbf4bc · fix(server): T5 weights names. (#582) · Updated 2023-07-12 11:01:42 +03:00
75
0
 Included
 ZIP  TAR.GZ
feat/better_tokens

a4fd6905d8 · fmt · Updated 2023-06-23 16:01:05 +03:00
102
2
 ZIP  TAR.GZ
add_integration_test

dca0fe2585 · Adding GPTQ integration tests. · Updated 2023-06-19 15:14:17 +03:00
105
19
 ZIP  TAR.GZ
add_gptq_docs

17837b1e51 · Adding docs about GPTQ usage. · Updated 2023-06-15 20:41:04 +03:00
105
19
 ZIP  TAR.GZ
quantization

fb0840944c · Reducing number of reps while autotuning. · Updated 2023-06-06 14:56:10 +03:00
156
9
 ZIP  TAR.GZ
remove_post_load_weights

7ccb8eefdc · TMP. · Updated 2023-05-15 17:43:32 +03:00
150
4
 ZIP  TAR.GZ
feat/improve_max_tokens

a963495315 · add logic to queue · Updated 2023-04-26 14:40:20 +03:00
189
2
 ZIP  TAR.GZ
feat/parse_logs

7caea42573 · feat(launcher): parse all shard logs · Updated 2023-04-15 22:25:02 +03:00
219
2
 ZIP  TAR.GZ
deploy/aml

47ac334a21 · 0.4.0 · Updated 2023-03-12 12:06:15 +03:00
312
9
 ZIP  TAR.GZ
megatron

60ed7b535c · first tests · Updated 2023-02-23 11:52:17 +03:00
296
1
 ZIP  TAR.GZ