Hugging Face's logo

baseten
/
btest-bloom-560m-A100-2a115dae-TP2

Transformers
Inference Endpoints
Model card Files Community
pankajroark commited on
Commit
6d8b612
•
1 Parent(s): 77e9c24

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +1 -1
  2. rank0.engine +1 -1
  3. rank1.engine +1 -1
config.json CHANGED
@@ -124,7 +124,7 @@
124
  "enable_xqa": true,
125
  "attention_qk_half_accumulation": false,
126
  "tokens_per_block": 64,
127
- "use_paged_context_fmha": false,
128
  "use_fp8_context_fmha": false,
129
  "multiple_profiles": false,
130
  "paged_state": true,
 
124
  "enable_xqa": true,
125
  "attention_qk_half_accumulation": false,
126
  "tokens_per_block": 64,
127
+ "use_paged_context_fmha": true,
128
  "use_fp8_context_fmha": false,
129
  "multiple_profiles": false,
130
  "paged_state": true,
rank0.engine CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2c007d577c89fa2a576756f2ab0145f5ea02b405700fa221bb2e8bae2f09e79
3
  size 1076655172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b866645fd515cedea56267d8815d806805c6d5600d06a058ea7035023823653f
3
  size 1076655172
rank1.engine CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e26598c0aa7aba8cc6e93c0d5211d346df39f66746eb9c3a4bb1c960d1a2fe23
3
  size 1076655172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88bc8b31a4ef5426b66317cd79f58ec867f2c151cf19d6e133d98a8bea577457
3
  size 1076655172