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
1,151 Commits 179 Branches 50 Tags 606 MiB

Default Branch

main

780531ec77 · chore: prepare 2.4.1 release (#2773) · Updated 2024-11-22 10:26:15 -07:00
 ZIP  TAR.GZ

Branches

add-quickstart-script

a6890cbea9 · feat: update readme and container version · Updated 2024-04-25 18:46:11 -06:00
495
2
 ZIP  TAR.GZ
skip-mistral-test

d7983d93be · fix: skip all mistral test to enable CI · Updated 2024-04-25 16:04:07 -06:00
495
1
 ZIP  TAR.GZ
fix_default_arg

885ce3354f · User argument should be gospel and never ignored. · Updated 2024-04-19 08:47:08 -06:00
507
1
 ZIP  TAR.GZ
fix-grammar-cleanup-bug

e6259d9fc0 · fix: reset grammar state when generation stops · Updated 2024-04-18 11:05:52 -06:00
507
1
 ZIP  TAR.GZ
llama-fused-compiled-mlp

9eeda34427 · feat: vendor precompiled llama mlp kernel · Updated 2024-04-16 16:07:00 -06:00
510
1
 ZIP  TAR.GZ
explore-static-triton-kernels

8ebb560f2f · feat: integrate triton compilations demo · Updated 2024-04-12 15:47:15 -06:00
514
1
 ZIP  TAR.GZ
improve_defaults

f66c9f340b · Update the doc. · Updated 2024-04-12 06:09:23 -06:00
520
15
 ZIP  TAR.GZ
tmp_medusa

10dd0150c0 · Dummy fix for medusa. · Updated 2024-04-12 04:12:09 -06:00
526
9
 ZIP  TAR.GZ
improve_launcher_defaults

b83aab9bb3 · Easier defaults for models stemmed from configs. · Updated 2024-04-11 06:48:39 -06:00
524
0
 Included
 ZIP  TAR.GZ
op-compilation-benchmarking

d0bc603fe6 · feat: explore compiled MLP bench · Updated 2024-04-08 20:36:09 -06:00
530
1
 ZIP  TAR.GZ
fix-grammar-fsm-batching

2762e6883e · fix: include fsm_grammar_states in FlashMistralBatch from_pb · Updated 2024-04-08 11:23:46 -06:00
530
1
 ZIP  TAR.GZ
tmp_torch_compile

78f87d5a0c · Temporary implem of torch.compile on our stuff. · Updated 2024-03-21 12:56:40 -06:00
550
1
 ZIP  TAR.GZ
test_rocm

c1095bb61a · add debug · Updated 2024-03-18 04:54:31 -06:00
588
26
 ZIP  TAR.GZ
router-grammar-compile

b5dcc87459 · fix: include shared python library during rust build step · Updated 2024-03-08 16:13:07 -07:00
557
8
 ZIP  TAR.GZ
bump-client-0.6.2

a7cc4dc9da · fix: bump client version · Updated 2024-03-04 07:29:27 -07:00
557
1
 ZIP  TAR.GZ
avoid-zero-seed

b47b161cab · feat: update more snapshots · Updated 2024-02-29 15:06:13 -07:00
570
4
 ZIP  TAR.GZ
adding_docs

960cc95a0e · Update speculation.md · Updated 2024-02-27 07:55:37 -07:00
569
3
 ZIP  TAR.GZ
feat/flash_decoding

a42dc2027b · update commit · Updated 2024-02-27 03:24:07 -07:00
569
2
 ZIP  TAR.GZ
fix-gemma-tokenization

cd57f9c632 · fix: avoid duplicate bos token · Updated 2024-02-23 07:53:18 -07:00
570
1
 ZIP  TAR.GZ
ci-amihalik-update-chat-completion-messages

5cdee2a591 · Merge branch 'amihalik-update-chat-completion-messages' into ci-amihalik-update-chat-completion-messages · Updated 2024-02-15 10:50:14 -07:00
583
3
 ZIP  TAR.GZ