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

feature/vlm-prefix-caching

69dd51069f · unique hash for each image token · Updated 2024-09-03 06:56:02 -06:00
157
5
 ZIP  TAR.GZ
feat/add-load-test

a258e8f66a · fix: Fix PR comments · Updated 2024-09-02 01:36:23 -06:00
158
12
 ZIP  TAR.GZ
upgrade_mlp_speculator

5838f2139f · Tied embeddings in MLP speculator. · Updated 2024-08-29 04:30:26 -06:00
164
47
 ZIP  TAR.GZ
avoid-cuda-graph-during-warmup-if-oom

e152cb022b · fix: also show total memory after full warmup · Updated 2024-08-22 11:57:51 -06:00
169
2
 ZIP  TAR.GZ
fix/op-trace-id

d33fb9ed2c · extracting traceparent from header to span · Updated 2024-08-21 03:28:50 -06:00
170
1
 ZIP  TAR.GZ
prefix_default

2652e209e7 · Updated flake lock · Updated 2024-08-21 01:15:10 -06:00
170
15
 ZIP  TAR.GZ
fix_exl2

b378fb4702 · Fixing exl2 (by disabling cuda graphs) · Updated 2024-08-14 11:44:54 -06:00
203
2
 ZIP  TAR.GZ
exl2

89707adbbb · Fixing exl2 (by disabling cuda graphs) · Updated 2024-08-14 11:41:29 -06:00
186
4
 ZIP  TAR.GZ
fix-repack-for-marlin

4b10c8c30b · fix: improve scales change and revert conditional · Updated 2024-08-14 10:38:15 -06:00
187
2
 ZIP  TAR.GZ
fix-release-tests

b84bb19ece · fix: prefer recent gptq changes · Updated 2024-08-12 09:51:19 -06:00
194
9
 ZIP  TAR.GZ
explore-t4-gemma-issues

7bc16deb48 · wip: debug gemma and flash · Updated 2024-08-09 17:08:54 -06:00
204
1
 ZIP  TAR.GZ
feature/radix-prefix-cache

7735b385dc · Prefix caching WIP · Updated 2024-08-09 08:52:59 -06:00
206
1
 ZIP  TAR.GZ
nix/cargo-clippy

9f039ad4b3 · flake: use rust-overlay · Updated 2024-08-09 07:02:57 -06:00
210
2
 ZIP  TAR.GZ
pr-2366-ci-branch

e219397ee1 · fix: adjust syntax typo again · Updated 2024-08-07 18:31:24 -06:00
222
4
 ZIP  TAR.GZ
feature/radix-prefix-cache-bench

f230da8d63 · Keeping the benchmark somewhere · Updated 2024-08-06 06:36:15 -06:00
231
17
 ZIP  TAR.GZ
inlcude-latest-release-on-commit-builds-tags

4379f0650a · feat: add release and sha tagged images · Updated 2024-08-05 11:13:52 -06:00
228
1
 ZIP  TAR.GZ
feature/no_repeat_ngram_size_ci

ab2ab2a0aa · pre-commit · Updated 2024-08-05 05:01:19 -06:00
233
16
 ZIP  TAR.GZ
fix/parse-mamba-config

060b2db0df · add 'mamba' as model config · Updated 2024-08-01 10:16:32 -06:00
230
1
 ZIP  TAR.GZ
fix-main-trtllm

31ebfd0dd7 · (launcher) default new server::run parameters to false for now · Updated 2024-07-31 03:06:52 -06:00
238
24
 ZIP  TAR.GZ
backends/trtllm-executor

8fad7ae5a2 · add some more basic info in README.md · Updated 2024-07-30 02:45:29 -06:00
344
82
 ZIP  TAR.GZ