Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
1,143 Commits 180 Branches 49 Tags 605 MiB

Default Branch

main

3c54488638 · nix: downgrade to outlines 0.1.3 (#2768) · Updated 2024-11-21 05:00:26 -07:00
 ZIP  TAR.GZ

Branches

docs/readme-nix

56e3b65c46 · Add a README section about using Nix · Updated 2024-11-21 02:00:26 -07:00
1
1
 ZIP  TAR.GZ
feat-backend-llamacpp

5335bf973b · feat(backend): multistream inference on CPU · Updated 2024-11-20 16:03:05 -07:00
23
65
 ZIP  TAR.GZ
feature/compressed-tensors-kv-cache-fp8

74a8a820ad · Use FP8 KV cache when specified by compressed-tensors · Updated 2024-11-20 07:25:50 -07:00
5
1
 ZIP  TAR.GZ
support-continue-final-message

fa577c9be2 · fix: remove continue_final_message chat request param · Updated 2024-11-19 14:24:18 -07:00
24
4
 ZIP  TAR.GZ
trtllm/cancellation

d2581ed606 · feat(backend): remove all the logs from hardware.hpp · Updated 2024-11-18 16:19:22 -07:00
15
5
 ZIP  TAR.GZ
enable-qwen2vl-video

0fd2ab3e89 · fix: remove unused deps and imports · Updated 2024-11-18 14:48:09 -07:00
10
12
 ZIP  TAR.GZ
ipex-moe

53b6f6e604 · Apply suggestions from code review · Updated 2024-11-18 04:28:07 -07:00
14
8
 ZIP  TAR.GZ
auto_max_prefill

627862c11a · Updated the flops calculation (checked with fvcore). · Updated 2024-11-11 06:31:32 -07:00
29
10
 ZIP  TAR.GZ
feat/limit

6297f1769f · feat: add payload limit · Updated 2024-11-05 08:38:21 -07:00
25
1
 ZIP  TAR.GZ
pr-2711-ci-branch

a604bfe450 · fix: run pre commit lints · Updated 2024-11-01 10:11:57 -06:00
33
2
 ZIP  TAR.GZ
trtllm-stop-words

3bb78a8266 · misc(deps): update ompi from 4.1.6 to 4.1.7rc1 to avoid strange deadlock · Updated 2024-10-28 10:24:08 -06:00
61
80
 ZIP  TAR.GZ
upgrade-outlines

7bc2c97bd9 · Check if allowed tokens is None (#2694) · Updated 2024-10-27 22:10:55 -06:00
39
3
 ZIP  TAR.GZ
git_v2.4.0

0a655a0ab5 · v2.4.0 · Updated 2024-10-25 15:12:49 -06:00
43
1
 ZIP  TAR.GZ
auto_length

e3db525917 · Fix integration mt0 (transformers update). · Updated 2024-10-24 03:54:11 -06:00
60
12
 ZIP  TAR.GZ
close_dl_thread

fe8d55dba9 · Clean both threads. · Updated 2024-10-21 06:49:07 -06:00
60
2
 ZIP  TAR.GZ
adjust-where-request-max-tokens-is-defaulted

b3917ff695 · fix: add limit to internal stream function too · Updated 2024-10-15 09:14:04 -06:00
71
2
 ZIP  TAR.GZ
feature/machete

c9e0f36dbc · Machete WIP · Updated 2024-10-14 07:46:00 -06:00
82
1
 ZIP  TAR.GZ
add-test-for-warmup-and-kvcache

99b1cf5948 · fix: rerun linter · Updated 2024-10-09 14:10:31 -06:00
83
6
 ZIP  TAR.GZ
add-rotary-embed-tests

130f9d16b5 · fix: rerun black lint · Updated 2024-10-09 12:44:41 -06:00
84
3
 ZIP  TAR.GZ
bugfix/moe-kernels-imports

e618ce3ada · Fix: make `moe_kernels` imports conditional · Updated 2024-10-08 05:05:28 -06:00
86
1
 ZIP  TAR.GZ