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
1,142 Commits 179 Branches 49 Tags 605 MiB

Default Branch

main

6ee8d6dd3b · fix: set outlines version to 0.1.3 to avoid caching serialization issue (#2766) · Updated 2024-11-20 16:09:39 -07:00
 ZIP  TAR.GZ

Branches

backends/trtllm

9815feb2e3 · Revert "Update devcontainer to use correct update content command path" · Updated 2024-06-28 07:26:45 -06:00
343
13
 ZIP  TAR.GZ
git_v2.1.0

192d49af0b · 2.1.0 names for release. · Updated 2024-06-28 00:20:59 -06:00
337
1
 ZIP  TAR.GZ
automodel-supports-flash-paged-attention

02ac45131f · some cleaning · Updated 2024-06-27 07:33:35 -06:00
343
4
 ZIP  TAR.GZ
feat/backend_abstraction

2bcc87bb02 · add dummy backend · Updated 2024-06-26 07:39:28 -06:00
343
5
 ZIP  TAR.GZ
ci2

c45551cfc4 · Using new cache. · Updated 2024-06-26 07:21:03 -06:00
343
1
 ZIP  TAR.GZ
temp_work

0dcf31a749 · Fixing gemma2. · Updated 2024-06-26 07:02:56 -06:00
343
1
 ZIP  TAR.GZ
bugfix/phi-exl2

7947c347b7 · exl2 phi does not use packed QKV/gate-up projections · Updated 2024-06-26 02:38:08 -06:00
343
1
 ZIP  TAR.GZ
multi-lora

a7556ba800 · fix: refactors and helpful comments · Updated 2024-06-24 07:39:56 -06:00
365
36
 ZIP  TAR.GZ
debug-torch-23

65506e19bf · update dockerfile · Updated 2024-06-20 09:36:46 -06:00
467
1
 ZIP  TAR.GZ
feat/backend_feature

56b16614de · continue refactoring · Updated 2024-06-20 08:59:38 -06:00
362
2
 ZIP  TAR.GZ
pr-2076-ci-run

48010f14b5 · fix: re update the docs · Updated 2024-06-19 19:05:47 -06:00
364
8
 ZIP  TAR.GZ
maintenance/docker-network

c1125781e0 · Try something · Updated 2024-06-19 01:33:45 -06:00
365
1
 ZIP  TAR.GZ
ci-patch

9fb7790928 · fix: update docker auth step · Updated 2024-06-18 09:49:43 -06:00
365
2
 ZIP  TAR.GZ
feat/page_re_alloc

fe9abad1a9 · mirror docker · Updated 2024-06-18 07:58:59 -06:00
365
19
 ZIP  TAR.GZ
feature/phi-3-small

5d2b93ba42 · Fixup residual, initial block attention config · Updated 2024-06-13 02:38:56 -06:00
378
3
 ZIP  TAR.GZ
debug-gpt2

64182534b6 · debug · Updated 2024-06-13 01:48:18 -06:00
382
60
 ZIP  TAR.GZ
amd-ci-fx

d3c7f63416 · Merge branch 'main' into amd-ci-fx · Updated 2024-06-10 07:10:04 -06:00
382
52
 ZIP  TAR.GZ
ci_amd2

41699e9bbf · . · Updated 2024-06-08 14:16:37 -06:00
384
50
 ZIP  TAR.GZ
support-phi3-small

cf8fdef9d3 · feat: adjust to load weights · Updated 2024-06-05 05:48:21 -06:00
397
1
 ZIP  TAR.GZ
set-num-blocks

bb37321b9f · allow to fix paged attention num blocks · Updated 2024-06-05 04:05:04 -06:00
407
1
 ZIP  TAR.GZ