huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-12 04:44:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Remove some comments.

Browse Source
This commit is contained in:
Nicolas Patry 2024-09-07 00:53:12 +02:00
parent 37790de5ca
commit c67bec168e
No known key found for this signature in database
GPG Key ID: 64AF4752B2967863
3 changed files with 1 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
backends/v3/src/radix.rs
View File

@ -76,9 +76,6 @@ impl Allocator for RadixAllocator {
&prefill_tokens.as_slice()[..prefill_tokens.len().saturating_sub(1)], &prefill_tokens.as_slice()[..prefill_tokens.len().saturating_sub(1)],
&mut blocks, &mut blocks,
); );
// Even if this allocation fails below, we need to increase he
// refcount to ensure that the prefix that was found is not evicted.
node_id node_id
} else { } else {
self.cache_blocks.root_id() self.cache_blocks.root_id()

1
integration-tests/conftest.py
View File

@ -398,7 +398,6 @@ def launcher(event_loop):
if not use_flash_attention: if not use_flash_attention:
env["USE_FLASH_ATTENTION"] = "false" env["USE_FLASH_ATTENTION"] = "false"
env["USE_PREFIX_CACHING"] = "0"
with tempfile.TemporaryFile("w+") as tmp: with tempfile.TemporaryFile("w+") as tmp:
# We'll output stdout/stderr to a temporary file. Using a pipe # We'll output stdout/stderr to a temporary file. Using a pipe

2
server/Makefile-flashinfer
View File

@ -1,2 +1,2 @@
install-flashinfer: install-flashinfer:
pip install flashinfer==0.1.4 -i https://flashinfer.ai/whl/cu124/torch2.4 pip install flashinfer==0.1.5 -i https://flashinfer.ai/whl/cu124/torch2.4