minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[AMD] Update amd k3 cookbook for fp8 kv cache (#33825)

Browse Source
This commit is contained in:
Thomas Wang
2026-08-05 23:35:38 -07:00
committed by GitHub
parent 8e11feb68e
commit dea07b348b
2 changed files with 6 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/src/snippets/configs/moonshotai/kimi-k3.jsx
+4
View File
@@ -962,6 +962,7 @@ export const config = {
"--trust-remote-code",
"--tp-size 8",
"--attention-backend triton",
"--kv-cache-dtype fp8_e4m3",
"--dtype bfloat16",
"--mem-fraction-static 0.85",
"--cuda-graph-max-bs 256",
@@ -988,6 +989,7 @@ export const config = {
"--trust-remote-code",
"--tp-size 8",
"--attention-backend triton",
"--kv-cache-dtype fp8_e4m3",
"--dtype bfloat16",
"--mem-fraction-static 0.85",
"--cuda-graph-max-bs 256",
@@ -1739,6 +1741,7 @@ export const config = {
"--trust-remote-code",
"--tp-size 8",
"--attention-backend triton",
"--kv-cache-dtype fp8_e4m3",
"--dtype bfloat16",
"--mem-fraction-static 0.85",
"--cuda-graph-max-bs 256",
@@ -1766,6 +1769,7 @@ export const config = {
"--trust-remote-code",
"--tp-size 8",
"--attention-backend triton",
"--kv-cache-dtype fp8_e4m3",
"--dtype bfloat16",
"--mem-fraction-static 0.85",
"--cuda-graph-max-bs 256",